{ "complete": true, "report": { "bucket": "emo_Concentration", "label": "Intense Concentration", "definition": { "id": "emo_Concentration", "category": "emotion", "head": "emo_Concentration", "pole": "high", "label": "Intense Concentration", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_concentration/full-v2-sealed/sealed-selected", "mission": "emotion_concentration", "format_status": "CANONICAL", "heldout": true, "qualified": true, "source_cfg": 2.5, "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": 6.338811335563659, "genuineness": 4.3134802317619325, "wer": 0.0022903225806451613, "identity": 0.5395072343945503, "voiceclap": -0.1040697633009404, "fitness": 0.8150341767951327, "steering_v2": 0.9573336358374873, "raw_target": 1.9839264607429505, "target_cdf": 0.9573336358374873, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.377174463272095, "genuineness": 4.260322151184082, "wer": 0.0, "identity": 0.5395072343945503, "fitness": 0.8118806898866776, "steering_v2": 0.9498758106777437 }, "none": { "n": 50, "ce": 6.300448207855225, "genuineness": 4.3666383123397825, "wer": 0.004580645161290323, "identity": null, "fitness": 0.8181876637035878, "steering_v2": 0.9647914609972309 } } } } ], "selected_wording": { "id": "manual-04d8f738e9e1", "general": "Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.", "inline": [ "Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.", "Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.", "Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger." ], "cfg": 2.5, "recipe": "P07", "strategy": "local-Gemma-mutation", "timing_syntax": "canonical", "canonical_labels": true, "neutral_event": "keep", "parent": "cfg-2.5", "origin": "exact_frozen_manual_recipe" }, "selection": { "manual_no_adapter": { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 1.775781232217002, "target_raw": 1.9679449498653412, "ce": 5.7364789009094235, "genuineness": 4.372726106643677, "identity": 0.5454636961221695, "wer": 0.020792483660130718, "valid_fraction": 0.95, "identity_delta": -0.03040682077407837, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": 1.8128906385443981, "target_raw": 1.995056438446045, "ce": 6.12427978515625, "genuineness": 4.325655734539032, "identity": 0.6050604939460754, "wer": 0.011437908496732025, "valid_fraction": 1, "identity_delta": 0.029189977049827575, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 1.775781232217002, "target_raw": 1.9679449498653412, "ce": 5.7364789009094235, "genuineness": 4.372726106643677, "identity": 0.5454636961221695, "wer": 0.020792483660130718, "valid_fraction": 0.95, "identity_delta": -0.03040682077407837, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": 1.7707031157260709, "target_raw": 1.9642349660396576, "ce": 5.92035174369812, "genuineness": 4.335069799423218, "identity": 0.5838129468262195, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": 0.007942429929971694, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": 1.7003906048905524, "target_raw": 1.9128658652305603, "ce": 6.105614495277405, "genuineness": 4.386219549179077, "identity": 0.6070802807807922, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.031209763884544373, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": 1.6988281037432622, "target_raw": 1.911724328994751, "ce": 6.169155931472778, "genuineness": 4.35389791727066, "identity": 0.5892835721373558, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.013413055241107941, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": 1.6896484360180835, "target_raw": 1.9050178229808807, "ce": 6.123485565185547, "genuineness": 4.338835418224335, "identity": 0.5535539567470551, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.02231656014919281, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": 1.6593750109629952, "target_raw": 1.8829005837440491, "ce": 6.109188747406006, "genuineness": 4.3636257410049435, "identity": 0.6004614755511284, "wer": 0.005555555555555555, "valid_fraction": 1, "identity_delta": 0.024590958654880524, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": 1.6496093583961613, "target_raw": 1.8757659673690796, "ce": 6.06828396320343, "genuineness": 4.431720805168152, "identity": 0.5755816079676151, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.0002889089286327362, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 1.6011718799397217, "target_raw": 1.8403783857822418, "ce": 5.882127594947815, "genuineness": 4.407871913909912, "identity": 0.5342580534517765, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.04161246344447136, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": 1.8128906385443981, "target_raw": 1.995056438446045, "ce": 6.12427978515625, "genuineness": 4.325655734539032, "identity": 0.6050604939460754, "wer": 0.011437908496732025, "valid_fraction": 1, "identity_delta": 0.029189977049827575, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": 1.8015624603547498, "target_raw": 1.9867802679538726, "ce": 6.060738444328308, "genuineness": 4.349818515777588, "identity": 0.5945109471678733, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.01864043027162552, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 1.7859375223084204, "target_raw": 1.9753649592399598, "ce": 6.014075207710266, "genuineness": 4.393123149871826, "identity": 0.5825420796871186, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0066715627908706665, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": 1.7625000050990676, "target_raw": 1.95824191570282, "ce": 6.042073130607605, "genuineness": 4.4464695930480955, "identity": 0.5443797588348389, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.031490758061409, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": 1.749218753505609, "target_raw": 1.948538863658905, "ce": 6.0587527513504025, "genuineness": 4.403164911270141, "identity": 0.5846231251955032, "wer": 0.005718954248366013, "valid_fraction": 1, "identity_delta": 0.00875260829925537, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": 1.7425781113918635, "target_raw": 1.9436873257160188, "ce": 6.118322777748108, "genuineness": 4.33883546590805, "identity": 0.5798352360725403, "wer": 0.008680555555555556, "valid_fraction": 1, "identity_delta": 0.003964719176292419, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": 1.7394531498898234, "target_raw": 1.9414042830467224, "ce": 6.051207208633423, "genuineness": 4.36676379442215, "identity": 0.589401875436306, "wer": 0.006458333333333333, "valid_fraction": 1, "identity_delta": 0.013531358540058136, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 1.7382812291575616, "target_raw": 1.9405480980873109, "ce": 5.889176750183106, "genuineness": 4.388416147232055, "identity": 0.5688376680016518, "wer": 0.006458333333333333, "valid_fraction": 1, "identity_delta": -0.0070328488945961, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 1.7308593935797274, "target_raw": 1.9351258337497712, "ce": 5.841719245910644, "genuineness": 4.3407182693481445, "identity": 0.5739714786410332, "wer": 0.009027777777777777, "valid_fraction": 1, "identity_delta": -0.0018990382552146912, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 1.7246093481980262, "target_raw": 1.9305596590042113, "ce": 5.763285446166992, "genuineness": 4.3570359468460085, "identity": 0.5767135672271252, "wer": 0.018914473684210526, "valid_fraction": 0.95, "identity_delta": 0.0008430503308773041, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": 1.7226562584771998, "target_raw": 1.92913276553154, "ce": 5.969397687911988, "genuineness": 4.440193438529969, "identity": 0.5562146693468094, "wer": 0.02263157894736842, "valid_fraction": 0.95, "identity_delta": -0.019655847549438478, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": 1.7097656525668339, "target_raw": 1.9197151124477387, "ce": 6.074439525604248, "genuineness": 4.330048954486847, "identity": 0.5572671338915824, "wer": 0.006666666666666666, "valid_fraction": 1, "identity_delta": -0.018603383004665373, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": 1.7082031106270035, "target_raw": 1.918573546409607, "ce": 6.102040314674378, "genuineness": 4.35483934879303, "identity": 0.5904736757278443, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.014603158831596375, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": 1.7042968414417619, "target_raw": 1.9157196938991548, "ce": 6.138576602935791, "genuineness": 4.294589340686798, "identity": 0.5749979943037034, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.0008725225925445557, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": 1.6964843764978512, "target_raw": 1.9100120425224305, "ce": 6.115542888641357, "genuineness": 4.317810678482056, "identity": 0.5583848964422942, "wer": 0.009215686274509804, "valid_fraction": 1, "identity_delta": -0.017485620453953743, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": 1.6960937308147583, "target_raw": 1.9097266435623168, "ce": 6.044058823585511, "genuineness": 4.38872994184494, "identity": 0.6112420648336411, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": 0.03537154793739319, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": 1.6935547133618332, "target_raw": 1.9078716814517975, "ce": 6.149696350097656, "genuineness": 4.378688216209412, "identity": 0.6022352367639542, "wer": 0.01388888888888889, "valid_fraction": 0.95, "identity_delta": 0.026364719867706297, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 1.6882812577123396, "target_raw": 1.9040189862251282, "ce": 5.8675329208374025, "genuineness": 4.3965750455856325, "identity": 0.5412947088479996, "wer": 0.02448722910216718, "valid_fraction": 0.95, "identity_delta": -0.034575808048248294, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": 1.6374999867424245, "target_raw": 1.866919070482254, "ce": 6.1677659273147585, "genuineness": 4.409754705429077, "identity": 0.5631175689399243, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.012752947956323623, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": 1.6341796779233138, "target_raw": 1.8644933104515076, "ce": 6.13480384349823, "genuineness": 4.336952590942383, "identity": 0.5804787687957287, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0046082518994808195, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": 1.5960937552902825, "target_raw": 1.8366683959960937, "ce": 6.157837557792663, "genuineness": 4.3692741870880125, "identity": 0.5327837899327278, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.04308672696352005, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": 1.583789028160967, "target_raw": 1.8276787757873536, "ce": 6.196955275535584, "genuineness": 4.424503326416016, "identity": 0.5669377774000168, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.008932739496231079, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 1.712109387970753, "target_raw": 1.9214274048805238, "ce": 5.855321073532105, "genuineness": 4.410382318496704, "identity": 0.5127490408718586, "wer": 0.0654861111111111, "valid_fraction": 0.95, "identity_delta": -0.06312147602438926, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 1.7117187096536282, "target_raw": 1.9211419820785522, "ce": 5.690696811676025, "genuineness": 4.323459124565124, "identity": 0.46324251815676687, "wer": 0.0665234778121775, "valid_fraction": 0.9, "identity_delta": -0.11262799873948097, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": 1.6339843550817674, "target_raw": 1.8643506109714507, "ce": 6.169553065299988, "genuineness": 4.433917498588562, "identity": 0.5758705168962479, "wer": 0.01129170966632267, "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": 1.6033203332946349, "target_raw": 1.8419480085372926, "ce": 6.188218331336975, "genuineness": 4.407558083534241, "identity": 0.5706567324697971, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.00521378442645073, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": 1.642773450550426, "target_raw": 1.870771771669388, "ce": 6.162801766395569, "genuineness": 4.4298379778862, "identity": 0.560830794274807, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.015039722621440887, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": 1.7347656056554126, "target_raw": 1.9379796445369721, "ce": 6.163993191719055, "genuineness": 4.344483852386475, "identity": 0.551127552986145, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.024742963910102844, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": 1.8126562478711392, "target_raw": 1.994885196685791, "ce": 6.243419885635376, "genuineness": 4.395508089065552, "identity": 0.6163848227262497, "wer": 0.011176359872012046, "valid_fraction": 0.98, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": 1.9576562629643792, "target_raw": 2.100819692611694, "ce": 5.963281888961792, "genuineness": 4.42400128364563, "identity": 0.5273979195952415, "wer": 0.02538678712591756, "valid_fraction": 0.98, "identity_delta": -0.08898690313100815, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": 1.87328126301537, "target_raw": 2.0391767811775208, "ce": 6.208472156524659, "genuineness": 4.39488046169281, "identity": 0.5744029092788696, "wer": 0.008488612836438923, "valid_fraction": 1, "identity_delta": -0.041981913447380066, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": 1.879609364107117, "target_raw": 2.0437999820709227, "ce": 6.180831642150879, "genuineness": 4.390989351272583, "identity": 0.6089745083451271, "wer": 0.006583850931677018, "valid_fraction": 1, "identity_delta": -0.0074103143811225895, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": -0.006328101091747082, "ci95_z": [ -0.08468746754443514, 0.08234377619645952 ], "language_deltas": { "en": 0.13437500076486017, "de": -0.06640614374818013, "fr": 0.07500002243589718, "nl": -0.1160156653145028, "es": -0.058593719596809826 }, "languages_improved": 2, "clear_gain": false, "delta_ce": 0.027640514373779297, "delta_genuineness": 0.0038911104202270508, "delta_wer": 0.0019047619047619048, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "adapter_vs_best_manual": { "n": 50, "delta_z": -0.08437499994900931, "ci95_z": [ -0.15437498934294885, -0.01101563064084341 ], "language_deltas": { "en": 0.03828122099905344, "de": -0.14179682818418612, "fr": -0.028124988017191255, "nl": -0.1980468858036494, "es": -0.09218751873907323 }, "languages_improved": 1, "clear_gain": false, "delta_ce": 0.24519026756286622, "delta_genuineness": -0.029120821952819825, "delta_wer": -0.016898174289478637, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 0.14500001509323993, "ci95_z": [ 0.06453126638075446, 0.2276562752021413 ], "language_deltas": { "en": 0.08828125771233959, "de": 0.2484374702979316, "fr": 0.025000018356643137, "nl": 0.26718754933347844, "es": 0.09609377976580682 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.28013799667358397, "delta_genuineness": 0.028493194580078124, "delta_wer": 0.014210427253905514, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 1.0, "reason": "No new configuration passes the held-out gates; retain standard fallback and inspect audio", "fallback_standard": true }, "reference_only": true, "updated": 1793035179.7136009 }, "rows": [ { "id": "emo_Concentration-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_Concentration-es-1", "key": "0020b264f3d31f671091fdf4d53bc807f2e6696cea567126bf89ce56af48b821", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "0a8e90cfacf36e3eb622c3036c832fffc7aa1efb87877621ce7edbadd9d91206", "generation_seconds_batch": 17.354506751988083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9491095542907715, "target_z": 1.7499998980186493, "ce": 5.704906940460205, "genuineness": 4.557555198669434, "identity": 0.6989853382110596, "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_Concentration/0020b264f3d31f671091fdf4d53bc807f2e6696cea567126bf89ce56af48b821.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "008ecb41fff9822e075d7693a6ce1838201cb93ae5c1098bbb744509913bd124", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "e9aa48005a0ed02ed040be19fbe472bef97dd79c64f7d71380b5f55513c56aa6", "generation_seconds_batch": 23.183909917017445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7950024604797363, "target_z": 1.539062651059876, "ce": 5.824047088623047, "genuineness": 4.519899368286133, "identity": 0.47177472710609436, "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_Concentration/008ecb41fff9822e075d7693a6ce1838201cb93ae5c1098bbb744509913bd124.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "01028fbbd724c28ee3b37f2f904ede44cdfd0c4d02837e30a36083a8a2082ec8", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "6e32c1d2f32d2be6935798074f0924c1941824d86c29790dda8c40e99f144751", "generation_seconds_batch": 24.03291548101697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6979718208312988, "target_z": 1.4062499719551285, "ce": 6.348263263702393, "genuineness": 4.557555198669434, "identity": 0.40483373403549194, "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_Concentration/01028fbbd724c28ee3b37f2f904ede44cdfd0c4d02837e30a36083a8a2082ec8.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "01147efcba39479c0ac34aa0eae3c0d1a063ce64621d431ef4530f269ad45492", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "826cf0880f1798c31ee4857ae05568b19cef6b573a422438437d43f30a95859d", "generation_seconds_batch": 23.942865655990317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5724029541015625, "target_z": 1.2343750089233683, "ce": 6.340320587158203, "genuineness": 4.494794845581055, "identity": 0.5145450830459595, "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_Concentration/01147efcba39479c0ac34aa0eae3c0d1a063ce64621d431ef4530f269ad45492.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "014742fe2d0cc6239a6891c410e40ab67a14666a4b8a32093ce242c6a9bb4098", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "06b6f5b7af50d8d9237789c064302268cbe1dd4e5122640c3a70540f988a8f82", "generation_seconds_batch": 24.580113149946555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8577868938446045, "target_z": 1.625000132575756, "ce": 6.09409761428833, "genuineness": 4.293961524963379, "identity": 0.7187868356704712, "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_Concentration/014742fe2d0cc6239a6891c410e40ab67a14666a4b8a32093ce242c6a9bb4098.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": "0182c16e7a75ddb399b1701e63b24737181819d9f66991b71dd8895a95af755a", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "089fae8bb4cae2edbe58ea9925c0875d9da55b80b0762b019bd60ad3aa1ddbcf", "generation_seconds_batch": 18.242076375056058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8577868938446045, "target_z": 1.625000132575756, "ce": 5.538110733032227, "genuineness": 4.444586753845215, "identity": 0.6026175022125244, "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_Concentration/0182c16e7a75ddb399b1701e63b24737181819d9f66991b71dd8895a95af755a.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "01b07f0b7e8e580c59859a7fedc9c92442abde36d9f84609ba2abe826075cf79", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "3890e514fb88ce0a521ea57f97e85a893dcf5a9c2bf8d5cb86f61d1b81dd5589", "generation_seconds_batch": 23.68769497598987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0061864852905273, "target_z": 1.8281251185533203, "ce": 6.316492557525635, "genuineness": 4.432034492492676, "identity": 0.6164842247962952, "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_Concentration/01b07f0b7e8e580c59859a7fedc9c92442abde36d9f84609ba2abe826075cf79.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "01bfcddab0b0ea253e2ae68ae2ed3cb6ff38c15837c83fa1a938dab5db6315ff", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5c7b3118a9b98a268a66425d9ed1ffd4e720c20a71a8045b5caf3dcbb6532eba", "generation_seconds_batch": 23.813022161950357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8920328617095947, "target_z": 1.6718750038243007, "ce": 6.046441555023193, "genuineness": 4.319066047668457, "identity": 0.5936317443847656, "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_Concentration/01bfcddab0b0ea253e2ae68ae2ed3cb6ff38c15837c83fa1a938dab5db6315ff.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": "01e5f92dbdf513062c4de5968b04c46bdad62673bf57535954bf3b70f11a5917", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e03a25a1a4aa2f4e1291aaacac11d975c1a3ed9a137605042d386a2ea8406393", "generation_seconds_batch": 20.989614055026323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6979718208312988, "target_z": 1.4062499719551285, "ce": 6.165581703186035, "genuineness": 4.432034492492676, "identity": 0.7012256979942322, "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_Concentration/01e5f92dbdf513062c4de5968b04c46bdad62673bf57535954bf3b70f11a5917.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "d31a70bd5a2756a8f70a6151c8a4776e806739dc0c56a548948a5c47bf68a86c", "generation_seconds_batch": 15.112490709987469, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3258163928985596, "target_z": 2.2656251134542527, "ce": 6.125868320465088, "genuineness": 4.413206577301025, "identity": 0.750838041305542, "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_Concentration/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "02026a7730caedc0fdb24804027013a341054f381f2219c945b3e7a9d7ba11cb", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "13cdc4d943098db65df465806b9194f264c6794206b5ecbf5bce974af587072b", "generation_seconds_batch": 23.635641342028975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4742159843444824, "target_z": 2.468750099431817, "ce": 6.062326908111572, "genuineness": 4.20609712600708, "identity": 0.634675145149231, "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_Concentration/02026a7730caedc0fdb24804027013a341054f381f2219c945b3e7a9d7ba11cb.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "0207395c4652bff6b65755e97a743ddab615aaddfd6bf907905d708ca18def42", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "5ca92ebad1a7bd01645ea726c4be54f2225e259a4a57a2110aae57fa5c64582a", "generation_seconds_batch": 17.807628431008197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5838183164596558, "target_z": 1.2500000203962702, "ce": 6.515059471130371, "genuineness": 4.406930446624756, "identity": 0.47965431213378906, "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_Concentration/0207395c4652bff6b65755e97a743ddab615aaddfd6bf907905d708ca18def42.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "02463d2e7dfc3eab887ce583f516228c9eeceb9f6050af4d4fdff618fa2461ab", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "80a5f66970340a379fe62303889206259091dda82bf3f3011371f566dd504cf6", "generation_seconds_batch": 24.31186221097596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9833557605743408, "target_z": 1.7968750956075163, "ce": 6.0305562019348145, "genuineness": 4.331617832183838, "identity": 0.580222487449646, "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_Concentration/02463d2e7dfc3eab887ce583f516228c9eeceb9f6050af4d4fdff618fa2461ab.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "025f1b075597ecdb0b25689c3dbca3563e311cfa24a87f3b0c1c4e0aa2a3e86c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "16f8a78a04b60535ee6ba1647f22a284a6d8dac6361e39a1c33ba4baa00521d1", "generation_seconds_batch": 23.42651846096851, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5381568670272827, "target_z": 1.1874999745046624, "ce": 6.1894097328186035, "genuineness": 4.469690799713135, "identity": 0.3668050169944763, "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_Concentration/025f1b075597ecdb0b25689c3dbca3563e311cfa24a87f3b0c1c4e0aa2a3e86c.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "02764529c55059512b1a69fdbd068a1f89f9d5a7319b83e74267a76879765854", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "31d548d6557f2f169bb5a01e0414a672c65a9f0332b44e888f00aae4fff1db2e", "generation_seconds_batch": 23.87076107400935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0518476963043213, "target_z": 1.8906248381046056, "ce": 5.959072113037109, "genuineness": 4.13078498840332, "identity": 0.6486590504646301, "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_Concentration/02764529c55059512b1a69fdbd068a1f89f9d5a7319b83e74267a76879765854.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "029145023256d88ef460b64608dd0c9992b55ed3ced8684f9feae4150aa7ca5a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "f2eb4839c689e905165c9b9751c6d7dc16b90ba044a8146dca67a16f701f6999", "generation_seconds_batch": 16.897414582083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9491095542907715, "target_z": 1.7499998980186493, "ce": 5.8875885009765625, "genuineness": 4.344170093536377, "identity": 0.6684894561767578, "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_Concentration/029145023256d88ef460b64608dd0c9992b55ed3ced8684f9feae4150aa7ca5a.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "0291e04186ead90e0bc35f5d4790cb74b6c219cbacc1833217a9564833c0a0a2", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "bc67b6f0920afd583c745d55d52a59b93220c468deddb4d6c77e78e851bfd895", "generation_seconds_batch": 18.202600185992196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9376943111419678, "target_z": 1.7343750497159085, "ce": 5.426913261413574, "genuineness": 4.482243061065674, "identity": 0.8090815544128418, "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_Concentration/0291e04186ead90e0bc35f5d4790cb74b6c219cbacc1833217a9564833c0a0a2.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": "02c0e653f596fa06ca091bac8c56c3041af2096a47c45a82ee46000aef940c22", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "310c11ea393372728832cf5ab4e8ed9727017a9708f41d904bc63e10b5c3613e", "generation_seconds_batch": 16.822206430020742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.166001319885254, "target_z": 2.046874952833625, "ce": 6.221180438995361, "genuineness": 4.306513786315918, "identity": 0.5552670955657959, "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_Concentration/02c0e653f596fa06ca091bac8c56c3041af2096a47c45a82ee46000aef940c22.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "02e40ea2da71559fa2f676ec1e0f535c6174cf3d61599d9b8a27c0aeebb0b961", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "c077d7c586ebfd355aadff43a77307f0c9b5d6a3308496641a8983936c12415a", "generation_seconds_batch": 22.26029272004962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6066489219665527, "target_z": 1.2812498801719128, "ce": 6.054384231567383, "genuineness": 4.149612903594971, "identity": 0.3954833745956421, "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_Concentration/02e40ea2da71559fa2f676ec1e0f535c6174cf3d61599d9b8a27c0aeebb0b961.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "0364f07be28d4739ee71bbd8fcebf321ae93be08b59f022be50b7f883c605836", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d065685eb08990b26f1294d3c2ae5e58c7d16f1a3adfbf07dc414c474b65515f", "generation_seconds_batch": 23.378940987982787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.166001319885254, "target_z": 2.046874952833625, "ce": 5.95112943649292, "genuineness": 4.331617832183838, "identity": 0.5895212292671204, "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_Concentration/0364f07be28d4739ee71bbd8fcebf321ae93be08b59f022be50b7f883c605836.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": "038533184a8f500cfb1db8e44b324c1e59f5277959f7bab21da64aebadf08497", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c7f173c64e8ea79b6f0df5525e7e11248c126dcafb9233372fd3da810e663cf5", "generation_seconds_batch": 22.018976658931933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.926278829574585, "target_z": 1.7187498750728454, "ce": 6.300607204437256, "genuineness": 4.306513786315918, "identity": 0.41758477687835693, "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_Concentration/038533184a8f500cfb1db8e44b324c1e59f5277959f7bab21da64aebadf08497.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": "0398ae79731c366e165a11c869c0ccae44b03c510c20c824d82d911e6ce19d01", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e38b3d3618843827916928f83a8a1fc4b8339385b4ca5d08f2fde3d19a348e94", "generation_seconds_batch": 18.34130750503391, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.000478744506836, "target_z": 1.8203125312317887, "ce": 6.41180419921875, "genuineness": 4.394378662109375, "identity": 0.6192477941513062, "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_Concentration/0398ae79731c366e165a11c869c0ccae44b03c510c20c824d82d911e6ce19d01.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "03d9a0bbf99ed575e8bc57fc2d865ed60c311f0f05b3c4a29e89c990276ebeee", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "f1194c9ff47f38a506326db0f72bfdf3a7269170fcf923111e9baa71830d985e", "generation_seconds_batch": 24.183744042995386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6523103713989258, "target_z": 1.3437499260635206, "ce": 6.221180438995361, "genuineness": 4.287685871124268, "identity": 0.2533072829246521, "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_Concentration/03d9a0bbf99ed575e8bc57fc2d865ed60c311f0f05b3c4a29e89c990276ebeee.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "042de56ccf489dc97d8f5386a0103669d95b56c90607a83cc85a46cbec16303f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b5c7c2205a47b460b75568a6225a96ed54025338d79e0f3a1732b1032e9c33f0", "generation_seconds_batch": 17.55088362901006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.971940279006958, "target_z": 1.7812499209644532, "ce": 5.911416053771973, "genuineness": 4.482243061065674, "identity": 0.5365927219390869, "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_Concentration/042de56ccf489dc97d8f5386a0103669d95b56c90607a83cc85a46cbec16303f.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "04435961a27b618084187152648929627e981b5ff3ca04e9af9881d7167bb532", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "de1a303c71ae4032f5b9017d2a8fbb1b69def23b182fdd78fc0e182aaa49ee73", "generation_seconds_batch": 23.183909917017445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.80641770362854, "target_z": 1.5546874993626165, "ce": 5.919358730316162, "genuineness": 4.645420074462891, "identity": 0.7134333848953247, "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_Concentration/04435961a27b618084187152648929627e981b5ff3ca04e9af9881d7167bb532.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "04ee338dc8d731f6a498c9e96fd58c0e2157c046e13341829d1194b6fb763b78", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "b06f611dcbeadf6e8c62246a5213c47ebab19968e4c4c4c9667dc101652e6ae6", "generation_seconds_batch": 24.050986264948733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0404324531555176, "target_z": 1.874999989801865, "ce": 6.435632705688477, "genuineness": 4.21237325668335, "identity": 0.6517670154571533, "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_Concentration/04ee338dc8d731f6a498c9e96fd58c0e2157c046e13341829d1194b6fb763b78.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "0537bbaec09054968f9a4c4a5f3f0b3341ba2896433ff41cc1c965498c630a9a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "3f44c5b71feb390ee4b1e96e1fda4c1ba5517e67092e8925096eb351cca7fec7", "generation_seconds_batch": 16.985800566966645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9376943111419678, "target_z": 1.7343750497159085, "ce": 6.046441555023193, "genuineness": 4.557555198669434, "identity": 0.7006940841674805, "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_Concentration/0537bbaec09054968f9a4c4a5f3f0b3341ba2896433ff41cc1c965498c630a9a.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "054406cceb6e8964a5db81b8921406e586ef476d35d172a43939e265cf8fe228", "bucket": "emo_Concentration", "phase": "wording", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "133a9a10151389cb52f0e1973c76db67215dbec4bb7e5ed098dd2e0088370159", "generation_seconds_batch": 17.47714376600925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9776480197906494, "target_z": 1.7890625082859848, "ce": 6.046441555023193, "genuineness": 4.65797233581543, "identity": 0.7325078248977661, "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_Concentration/054406cceb6e8964a5db81b8921406e586ef476d35d172a43939e265cf8fe228.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": "056fb99cd51ae439bb6b2469dbe72b126c8b3f2ae7e7ad1e1134ba1ec04ed820", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "1e443ebd5c52b5f9e9ae597dfe2c48fd6e11fd1032c974f41567ec4a72300390", "generation_seconds_batch": 18.06512235593982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.15458607673645, "target_z": 2.0312501045308844, "ce": 6.300607204437256, "genuineness": 4.406930446624756, "identity": 0.4187777638435364, "hypothesis": "I wrote uh 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": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/056fb99cd51ae439bb6b2469dbe72b126c8b3f2ae7e7ad1e1134ba1ec04ed820.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "05799e5c7d17ef202884e790c910ab88eb662c40bc269ae3b15d217b5322c605", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "57ba3fac996d8f360b33ffd9070e98a9fb03191857f8963c6096b45e4a7a9707", "generation_seconds_batch": 21.201404894934967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.880617618560791, "target_z": 1.6562501555215599, "ce": 5.629451274871826, "genuineness": 4.3127899169921875, "identity": 0.624322772026062, "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_Concentration/05799e5c7d17ef202884e790c910ab88eb662c40bc269ae3b15d217b5322c605.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "05952af960bea5812ab10f33b4e0d37e87e62f32f0f7d8b9ad150b86b4d6c0b6", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "f54d933d9a2d8595e817224b1ddc6582940bf6d7c9cbe9af5efe6e07efce5338", "generation_seconds_batch": 23.629965062020347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.834956169128418, "target_z": 1.593750109629952, "ce": 6.173524379730225, "genuineness": 4.7332844734191895, "identity": 0.7968239784240723, "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_Concentration/05952af960bea5812ab10f33b4e0d37e87e62f32f0f7d8b9ad150b86b4d6c0b6.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "7afda04059bc5bb9690b3921c95d024a0ca2e9c554021e2a7c6f81e0ebc3be24", "generation_seconds_batch": 18.221175000071526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.241357684135437, "target_z": 0.7812500025495338, "ce": 6.403861999511719, "genuineness": 4.7081804275512695, "identity": 0.5981146693229675, "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_Concentration/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "05aaafbb64cf70705cc425771d3a3f311fba82297ad9d6449b23106bb92df0d9", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "535bf2c0f6462894a331da63172f87f78ba0f716be90ecd872057f474d416b3c", "generation_seconds_batch": 24.0639628469944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2230780124664307, "target_z": 2.124999847027974, "ce": 5.967014789581299, "genuineness": 4.507347106933594, "identity": 0.7202261686325073, "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_Concentration/05aaafbb64cf70705cc425771d3a3f311fba82297ad9d6449b23106bb92df0d9.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": "05b747d0676b702be9755c9d96765c097a01bc5839b536c7af0ba9c402e15a9a", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3a32b55123c2ad27f77e013f161bcdd363c5c501cf4b14224ae12e3771d89cfe", "generation_seconds_batch": 23.94703916599974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9833557605743408, "target_z": 1.7968750956075163, "ce": 5.982900142669678, "genuineness": 4.406930446624756, "identity": 0.8548609018325806, "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_Concentration/05b747d0676b702be9755c9d96765c097a01bc5839b536c7af0ba9c402e15a9a.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": "06517737fb2b445043e5592d9e14f2bc712d4db657b4ae647eac24defc3f6b2d", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7ea7a07764371e996792d726b44f51c4671d005ba159a3c80ed75ff6e9ec8ff8", "generation_seconds_batch": 14.740981984999962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5267415046691895, "target_z": 1.1718749630317604, "ce": 6.165581703186035, "genuineness": 4.457139015197754, "identity": 0.6505265831947327, "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_Concentration/06517737fb2b445043e5592d9e14f2bc712d4db657b4ae647eac24defc3f6b2d.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "0674e42eee15eff2fdce23781d854c09991545719c54803ed2a9182162219f08", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "c75e5c7609d3871ccb127e2bf80ad29146c186e71c049040577c4acdec46154d", "generation_seconds_batch": 16.99177124002017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2014038562774658, "target_z": 0.7265623808092962, "ce": 6.213237762451172, "genuineness": 4.65797233581543, "identity": 0.5088949203491211, "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_Concentration/0674e42eee15eff2fdce23781d854c09991545719c54803ed2a9182162219f08.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "06a7ed07e8cf7f58ef359a526aff3460a69f53a55751c28f1ee3a3ec467b4a50", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "e5b65f6701bb4b3a761f99b842b4e8a5f5709f7e29728840bb3eea4df82aa360", "generation_seconds_batch": 16.99177124002017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4468340873718262, "target_z": 1.0625000458916078, "ce": 6.022613525390625, "genuineness": 4.356721878051758, "identity": 0.6542000770568848, "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_Concentration/06a7ed07e8cf7f58ef359a526aff3460a69f53a55751c28f1ee3a3ec467b4a50.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "079bb3cc3d4d2ebbd3010fc10d2ecd60dc8e97d91407836443e8ac5095b7663b", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f4d5229f02e456a4da349df058329c4fc3813d5fe02a1156bd6765865912b85e", "generation_seconds_batch": 23.823983412003145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.485631227493286, "target_z": 2.484374947734558, "ce": 5.935244083404541, "genuineness": 4.15588903427124, "identity": 0.6132798194885254, "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_Concentration/079bb3cc3d4d2ebbd3010fc10d2ecd60dc8e97d91407836443e8ac5095b7663b.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "08399d266f9c918accd20dcd27a276277e74bdd456d03c6671e835c7eeac9a51", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c9bc6aaccdf16f342fa32ed38f752a1082bb9dba2e2354dc056509d6cfdddcb5", "generation_seconds_batch": 22.25641827308573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.549572229385376, "target_z": 1.2031249859775643, "ce": 6.252951145172119, "genuineness": 4.15588903427124, "identity": 0.3541635274887085, "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_Concentration/08399d266f9c918accd20dcd27a276277e74bdd456d03c6671e835c7eeac9a51.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "08464ca1ae5dead8f192eb4e2b9f95a051d54f45a6faa59ef665b9ac2a359eb3", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "a8ce6aedfed8c2a15657d77d762ccae3f31ca3c34bfe2219efe43252ab69280b", "generation_seconds_batch": 23.1027156409109, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7550485134124756, "target_z": 1.4843748661494771, "ce": 4.855537414550781, "genuineness": 4.444586753845215, "identity": 0.4660075008869171, "hypothesis": "Y la puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/08464ca1ae5dead8f192eb4e2b9f95a051d54f45a6faa59ef665b9ac2a359eb3.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": "08915c004fd4d6b53e19a01a4f7154c84438c1bff3834770dde763e430262a26", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "62e71782c1a8a87dc575e7c54259cd35f50bbf5b284dd2fe9879d194a1199548", "generation_seconds_batch": 18.044811928994022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2230780124664307, "target_z": 2.124999847027974, "ce": 6.268836498260498, "genuineness": 4.149612903594971, "identity": 0.6999968886375427, "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_Concentration/08915c004fd4d6b53e19a01a4f7154c84438c1bff3834770dde763e430262a26.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "08b0b2c1ffea3e7dab416e89f99f461fcd6c5e9988b3b2d1603dccb2b49164e2", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "f9d978c13a226c2776d8e9ab4b370173a7b57ee61542d762a3425e5caa8cde80", "generation_seconds_batch": 23.0887709580129, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9376943111419678, "target_z": 1.7343750497159085, "ce": 5.863759994506836, "genuineness": 4.469690799713135, "identity": 0.8228812217712402, "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_Concentration/08b0b2c1ffea3e7dab416e89f99f461fcd6c5e9988b3b2d1603dccb2b49164e2.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "08d38cbc96820a82e0a67fc4bd4068af9c78722a753a377b6334be2c693cdd8f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "189f8ff6a226839dfd3e0ec05e4286d9d9281ad850420037c2c9804442b74ab8", "generation_seconds_batch": 23.894188830046915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.074678421020508, "target_z": 1.9218748610504095, "ce": 6.395919322967529, "genuineness": 4.042920112609863, "identity": 0.6422233581542969, "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_Concentration/08d38cbc96820a82e0a67fc4bd4068af9c78722a753a377b6334be2c693cdd8f.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "08ebad0fbc02938ea6d49fab03ef1433f424c8dd2b7063249d86ffd748ed4d20", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "c1ebbce9d7a2257eb6ff3f9109e70b3f204134fe2423f901642458df31ff66f0", "generation_seconds_batch": 18.220657674013637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0860939025878906, "target_z": 1.9375000356934728, "ce": 6.149696350097656, "genuineness": 4.444586753845215, "identity": 0.8047351837158203, "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_Concentration/08ebad0fbc02938ea6d49fab03ef1433f424c8dd2b7063249d86ffd748ed4d20.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": "097aa3f04043c890546c6d8e1829620c4f59193af3dfa9d2aea7802f0f6f5b52", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "452d652d4c25e9910caef44021b74398c08107885dc6b0b5439d9d356dcaeb38", "generation_seconds_batch": 17.079252996947616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.542707920074463, "target_z": 2.5624998419289065, "ce": 6.300607204437256, "genuineness": 4.344170093536377, "identity": 0.18013685941696167, "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_Concentration/097aa3f04043c890546c6d8e1829620c4f59193af3dfa9d2aea7802f0f6f5b52.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": "09bbfeba1516daced3524fc49f3b92ccdc5ef4f68d38bc2a8262e20a5900358c", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "62a9a1b467cad70a2c6b985338c9d270013d35cae9ab31e8d2862de5d397ddca", "generation_seconds_batch": 25.30103811796289, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3326804637908936, "target_z": 0.9062499311625882, "ce": 6.173524379730225, "genuineness": 4.482243061065674, "identity": 0.6705347299575806, "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_Concentration/09bbfeba1516daced3524fc49f3b92ccdc5ef4f68d38bc2a8262e20a5900358c.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "0a3a8ffd7fcdc1f01c791b53b5cebd895437af385b269fa1dbb7e1e90a7c1012", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "62603f4c1e35118e96917b3cf5758026f4e7f83781b1278bd63180a91c170711", "generation_seconds_batch": 23.762027853983454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9833557605743408, "target_z": 1.7968750956075163, "ce": 6.117925643920898, "genuineness": 4.319066047668457, "identity": 0.7994517683982849, "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_Concentration/0a3a8ffd7fcdc1f01c791b53b5cebd895437af385b269fa1dbb7e1e90a7c1012.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "0a6b552df6bf584431be819215d30f9df76ace1ef73788094ed6d2e0718724a0", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cdc8febae53b8a889773cd66d7c399767f914b78d6fcbc70e4261375f5293952", "generation_seconds_batch": 24.017315658042207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6180644035339355, "target_z": 1.2968750548149761, "ce": 6.252951145172119, "genuineness": 4.469690799713135, "identity": 0.4135255813598633, "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_Concentration/0a6b552df6bf584431be819215d30f9df76ace1ef73788094ed6d2e0718724a0.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "0aed5ba1892cff46b8d432f3dee00dde40d3baf273ab2bcf5f799f8366010e19", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "6edba3e624b9b1bfdbf60c438a104ffa00cfe4be1560a0bd33ae6726ce731972", "generation_seconds_batch": 23.706367776961997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0975091457366943, "target_z": 1.9531248839962134, "ce": 6.157639026641846, "genuineness": 4.557555198669434, "identity": 0.6292229890823364, "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_Concentration/0aed5ba1892cff46b8d432f3dee00dde40d3baf273ab2bcf5f799f8366010e19.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "0b7a9e74a19e5c0d0f252b591dab6ee1db02a013c0fea775fc37b9884ccc5501", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "cfec8031af20f564218621a742ee340c319889555dcd1345e7db61ae415ab55e", "generation_seconds_batch": 21.852671992965043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8463714122772217, "target_z": 1.6093749579326928, "ce": 6.229123115539551, "genuineness": 4.086852550506592, "identity": 0.2763243615627289, "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_Concentration/0b7a9e74a19e5c0d0f252b591dab6ee1db02a013c0fea775fc37b9884ccc5501.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "0bbe12d32299c100f3d0b846ed430538e14c5dc1ac748fdf194b1ad46da390c3", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "ef806e11b75134701f9d00b14b203d706261ca2d3670467820d7b1512a22b5f0", "generation_seconds_batch": 24.278018030920066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1431705951690674, "target_z": 2.0156249298878213, "ce": 5.847874641418457, "genuineness": 3.9927117824554443, "identity": 0.5226326584815979, "hypothesis": "La porte était 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_Concentration/0bbe12d32299c100f3d0b846ed430538e14c5dc1ac748fdf194b1ad46da390c3.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "0bf6734fcbc5b96a977e07b087709d0cb9a514e0b29105e2d56b5068cb1119cf", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d2f9d6ea07ec9340a78800e6d058be346c05d6d22636c8565d13b6663f3200a0", "generation_seconds_batch": 21.607821582932957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.926278829574585, "target_z": 1.7187498750728454, "ce": 5.998785495758057, "genuineness": 4.425758361816406, "identity": 0.6028823256492615, "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_Concentration/0bf6734fcbc5b96a977e07b087709d0cb9a514e0b29105e2d56b5068cb1119cf.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "0c8f27c8a731bd5e9e832b1923cf7cd3e0b4bf526ec26ccf57b68d9cb29bd6c0", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "c508d7e6e7bef8cda07799bd2fa9d89b7b71e246703c4430dbac77df282afc1c", "generation_seconds_batch": 22.030181554029696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.046140193939209, "target_z": 1.8828125771233966, "ce": 5.816103935241699, "genuineness": 4.519899368286133, "identity": 0.6390403509140015, "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_Concentration/0c8f27c8a731bd5e9e832b1923cf7cd3e0b4bf526ec26ccf57b68d9cb29bd6c0.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": "0caae04b5d2d743ac911d8ce1bd90691cbc76ec8b376f7af996b868db51299aa", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "660756a2ea3540c1a249cf6bf7f1944b148f7c7be73cb387a7a069db71d551ea", "generation_seconds_batch": 15.927424791036174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.029017210006714, "target_z": 1.8593751414991242, "ce": 6.062326908111572, "genuineness": 4.457139015197754, "identity": 0.4693065881729126, "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_Concentration/0caae04b5d2d743ac911d8ce1bd90691cbc76ec8b376f7af996b868db51299aa.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "a3455241b219d2afce1f253a809675fc0ac3c20bf0dbe80c816ddd848ebc10e2", "generation_seconds_batch": 18.437401100993156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8851685523986816, "target_z": 3.0312498597756425, "ce": 6.141753673553467, "genuineness": 4.425758361816406, "identity": 0.7231638431549072, "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_Concentration/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.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": "0dead4f8de4d9bde3da46cf83a5370c2459d27286cf8a0e5f044686de468fc83", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "4494a923a6cecab89feea174cdd2d9359b690f87acb26514aa645b006714453d", "generation_seconds_batch": 15.364080565050244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.211662769317627, "target_z": 2.109374998725233, "ce": 5.863759994506836, "genuineness": 4.444586753845215, "identity": 0.6895899772644043, "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_Concentration/0dead4f8de4d9bde3da46cf83a5370c2459d27286cf8a0e5f044686de468fc83.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "0e8259ac1c1385344bc2c48bccd835c67b50afdb3a9366e9f6ad3eb0682b2d99", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0386530b7de44a2847e8138bf4df8494934b35630084e827973e1ee864d18a2c", "generation_seconds_batch": 18.186003855080344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1032168865203857, "target_z": 1.960937471317745, "ce": 5.796247482299805, "genuineness": 4.394378662109375, "identity": 0.9098902940750122, "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_Concentration/0e8259ac1c1385344bc2c48bccd835c67b50afdb3a9366e9f6ad3eb0682b2d99.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "0eea3353bad8ff0cd312751846fc5dbb29a9bbcbd2a43530c40cbf3b95edd77d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "16512fcb73cc3279b32714acd165e049e8dec591a38e60e19484605498ae3746", "generation_seconds_batch": 24.196402541943826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.926278829574585, "target_z": 1.7187498750728454, "ce": 5.863759994506836, "genuineness": 4.482243061065674, "identity": 0.5457578897476196, "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_Concentration/0eea3353bad8ff0cd312751846fc5dbb29a9bbcbd2a43530c40cbf3b95edd77d.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "0f66e480a02e782da24e47e91dbd3966030c41a8ee5abd578ca7d0950c87c9b1", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "a64e47255027399330c8c970c04fc618cd7bf9324b04fb2f94b404a874aa7c05", "generation_seconds_batch": 22.764010068029165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5997848510742188, "target_z": 2.6406250624635774, "ce": 5.95112943649292, "genuineness": 4.413206577301025, "identity": 0.525983989238739, "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_Concentration/0f66e480a02e782da24e47e91dbd3966030c41a8ee5abd578ca7d0950c87c9b1.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "1080f59214116506075eb73205aa0b8ca6823b02dc120f685a6db0e7395686bf", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "ab9aa125379c99e5c8a33c8b3037918472db4954f1a89d53021e7f3c043ac19f", "generation_seconds_batch": 25.25904701196123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0404324531555176, "target_z": 1.874999989801865, "ce": 6.38797664642334, "genuineness": 4.162164688110352, "identity": 0.5576891899108887, "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_Concentration/1080f59214116506075eb73205aa0b8ca6823b02dc120f685a6db0e7395686bf.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": "108a2fc7efb54a4d76e2d18a193915caf66b3172ed52ce38b174298c32136960", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "52401855b53ee8815919132d455d9424371c87c3ee6bb66b7a8bb0d4735549f6", "generation_seconds_batch": 15.030253333970904, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9947710037231445, "target_z": 1.8124999439102571, "ce": 6.086154937744141, "genuineness": 4.444586753845215, "identity": 0.6769396662712097, "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_Concentration/108a2fc7efb54a4d76e2d18a193915caf66b3172ed52ce38b174298c32136960.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "1092f53914719c3049145aa354f55fe90af5241cdf21b4a9fdcd883d007d5ea5", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "06351ff174d813b47522b2e6959207b2161df5d8cd6f20926303475c33229ab5", "generation_seconds_batch": 24.580113149946555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9605250358581543, "target_z": 1.7656250726617124, "ce": 5.959072113037109, "genuineness": 4.582659721374512, "identity": 0.712403416633606, "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_Concentration/1092f53914719c3049145aa354f55fe90af5241cdf21b4a9fdcd883d007d5ea5.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "10af551bb7c2e054dc45c0c635067900f5a98344dece46c634ddc7c3e60e42ff", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "592fd496c7fdb89b4c84f883fdf86ccbaf3dcdc8f96dcc58d4c73dcf309e7667", "generation_seconds_batch": 23.354489612975158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9890632629394531, "target_z": 1.8046873565887254, "ce": 5.935244083404541, "genuineness": 4.331617832183838, "identity": 0.6744286417961121, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/10af551bb7c2e054dc45c0c635067900f5a98344dece46c634ddc7c3e60e42ff.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "10be8280b8aaf3fade724d893b8a792df3fd69db12a04ec7531c5616f017bea3", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc292dae0a177222939d72b8de902a1bbdcf27e0fde25c4b775e51bc3ac36863", "generation_seconds_batch": 15.719984838971868, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3828930854797363, "target_z": 2.3437500076486013, "ce": 5.692992687225342, "genuineness": 4.344170093536377, "identity": 0.4940686523914337, "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_Concentration/10be8280b8aaf3fade724d893b8a792df3fd69db12a04ec7531c5616f017bea3.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": "10da97c99325cb2f24d543a49c1ebf0ddcb346ea1bf1d1fb3fb10bc4f00e9d54", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "c51d2e7d929cf3c4c37a1164a74cf19e098600400905c11a15de4d24773a6b94", "generation_seconds_batch": 18.242076375056058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.000478744506836, "target_z": 1.8203125312317887, "ce": 5.704906940460205, "genuineness": 4.369274139404297, "identity": 0.7164323329925537, "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_Concentration/10da97c99325cb2f24d543a49c1ebf0ddcb346ea1bf1d1fb3fb10bc4f00e9d54.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "11351ece311ed6c80ac7348fc7f18f1daae9646c32d9077098eee3d2d7d0d155", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "0d66f366639884e3cd2af34013d1179043a1d1382126a0fb4453933c9a87ba5c", "generation_seconds_batch": 25.6741333110258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8121254444122314, "target_z": 1.562500086684148, "ce": 6.1894097328186035, "genuineness": 4.645420074462891, "identity": 0.7001981139183044, "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_Concentration/11351ece311ed6c80ac7348fc7f18f1daae9646c32d9077098eee3d2d7d0d155.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "11499863bd6c6686e5b44334be56e7f5a721ad8b3d40494d713ab2ea633f988a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "3ba449b28b713aeb224101455913cfb31cfabcf29876f38809347f3fa8191b32", "generation_seconds_batch": 23.868621479021385, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6922640800476074, "target_z": 1.398437384633597, "ce": 5.935244083404541, "genuineness": 4.18726921081543, "identity": 0.6991543173789978, "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_Concentration/11499863bd6c6686e5b44334be56e7f5a721ad8b3d40494d713ab2ea633f988a.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "12813128be7368c0172dbf866a7850630730edcd0e8990bef149bb876752e0e1", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "2f107e7a1fea2ad0193ba1d5474d6d81d248a8e1dff6949879340b6731a017ba", "generation_seconds_batch": 21.014710027026013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7093873023986816, "target_z": 1.4218751465981918, "ce": 6.181467056274414, "genuineness": 4.281409740447998, "identity": 0.26317059993743896, "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_Concentration/12813128be7368c0172dbf866a7850630730edcd0e8990bef149bb876752e0e1.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "3044a55c4e8eac961df7560b44633e9097c17a189d9bfe7d8779b65d54d17fe2", "generation_seconds_batch": 17.186505028046668, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3155574798583984, "target_z": 0.8828124955383159, "ce": 6.1020402908325195, "genuineness": 4.570107460021973, "identity": 0.7337747812271118, "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_Concentration/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "132f0c870c25a12f6de1a2992e76da2e1984209bc7a67dcca8964b5b713e43fd", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "931536e6a0b410d27adc981c4f148cb15524be946d8735861769abbbe9784bad", "generation_seconds_batch": 23.46915988600813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3258163928985596, "target_z": 2.2656251134542527, "ce": 5.967014789581299, "genuineness": 4.325342178344727, "identity": 0.5976320505142212, "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_Concentration/132f0c870c25a12f6de1a2992e76da2e1984209bc7a67dcca8964b5b713e43fd.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "13e180ffadb1c3a2b554bc89e2b6a3e5e77d0624a40d6c1e60b8b90f0dcefd0a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "be485cf1a9642e57a57acd5ee13ac451a6de4a50412b405c83a249433ef6e0c8", "generation_seconds_batch": 24.081029778928496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7664639949798584, "target_z": 1.5000000407925402, "ce": 6.205295085906982, "genuineness": 3.9801597595214844, "identity": 0.28544050455093384, "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_Concentration/13e180ffadb1c3a2b554bc89e2b6a3e5e77d0624a40d6c1e60b8b90f0dcefd0a.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "146b1dee9efd5ba92fa824f164beb28ce85b2e2c6d7986f409d8d979c8ae49ee", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "3dffcd835ab1a0b4586592da362f7c0b00d7d21ee227ac3e4152e0980376abbf", "generation_seconds_batch": 23.1027156409109, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6922640800476074, "target_z": 1.398437384633597, "ce": 5.4944257736206055, "genuineness": 4.3881025314331055, "identity": 0.6155408620834351, "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_Concentration/146b1dee9efd5ba92fa824f164beb28ce85b2e2c6d7986f409d8d979c8ae49ee.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "1496de2522fd26765e0c2e57a5deeb52879ab83366fb631c7aecb9cf97d3ca82", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "85785070f11cbd89c70607409386e392debec207e6af46ed9e544666a8142b07", "generation_seconds_batch": 23.719796108081937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7550485134124756, "target_z": 1.4843748661494771, "ce": 6.117925643920898, "genuineness": 4.457139015197754, "identity": 0.570993959903717, "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_Concentration/1496de2522fd26765e0c2e57a5deeb52879ab83366fb631c7aecb9cf97d3ca82.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "15396ffdf095ac00105b46bc5515f69132d2562d77b0681e621452d15095977e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4c3f15a2958de880903e27df975d587af95443ddf48fe86e20902203e988c6ce", "generation_seconds_batch": 24.08483943901956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.549572229385376, "target_z": 1.2031249859775643, "ce": 6.125868320465088, "genuineness": 4.469690799713135, "identity": 0.07174085080623627, "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_Concentration/15396ffdf095ac00105b46bc5515f69132d2562d77b0681e621452d15095977e.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "da956aa45cdcb4ec29997b738dcf887e2a3e896abbce19d11541a6841033a8f5", "generation_seconds_batch": 17.494849067996256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.245908737182617, "target_z": 2.1562498699737778, "ce": 6.403861999511719, "genuineness": 4.281409740447998, "identity": 0.5488981008529663, "hypothesis": "Die Straße führ hinter der Brücke nach links. Geh weiter bis zum kleinen Holztur. Ich warte auf der anderen Seite.", "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_Concentration/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "158b81bc873b8df398b1cdb832357cdfc57ccb1b61e34d1ad9dbd546ee93d322", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "df0ef09381999978b84f0344bfe166ecd27dfdcbb420ac74e5051ee9bb086242", "generation_seconds_batch": 25.104769651894458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.080386161804199, "target_z": 1.929687448371941, "ce": 6.046441555023193, "genuineness": 4.174716949462891, "identity": 0.640548586845398, "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_Concentration/158b81bc873b8df398b1cdb832357cdfc57ccb1b61e34d1ad9dbd546ee93d322.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": "15e3ce89e8048a1dd63a1542b7a991f5e12c5afc119a22aa653d2edbfcf4483f", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "a1feec723d1a0c2ac75797650678013709306bb195225345b0d3d096034add8d", "generation_seconds_batch": 16.757847122033127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4285545349121094, "target_z": 2.406250053540209, "ce": 5.967014789581299, "genuineness": 4.457139015197754, "identity": 0.6756452322006226, "hypothesis": "De sleutels liggen op de keukentafel. Ik skek in de la en daarna naast het raam. Neem ze mee als je weggaat.", "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_Concentration/15e3ce89e8048a1dd63a1542b7a991f5e12c5afc119a22aa653d2edbfcf4483f.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": "15eae9abde14c3daf2143cda79c630c5c005dbc467e8c1cda4c0a31fb2faf1a6", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8824922c3595b8e69305381dce840f2979d1c578651ff94ad7e619df89932ef7", "generation_seconds_batch": 23.984171253978275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.108924627304077, "target_z": 1.9687500586392768, "ce": 6.3641486167907715, "genuineness": 4.18099308013916, "identity": 0.24030974507331848, "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_Concentration/15eae9abde14c3daf2143cda79c630c5c005dbc467e8c1cda4c0a31fb2faf1a6.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "160ec7632b9d6072486f121a7010e3770ee6be69746617d33ed4c24e26e9b1fb", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "daf956939e1917247757f047772f5f57daaf58d5091dbe15eef025c4cf161caf", "generation_seconds_batch": 22.730919800000265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0860939025878906, "target_z": 1.9375000356934728, "ce": 5.895530700683594, "genuineness": 4.457139015197754, "identity": 0.5844958424568176, "hypothesis": "", "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_Concentration/160ec7632b9d6072486f121a7010e3770ee6be69746617d33ed4c24e26e9b1fb.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "16a7638e11fb86925a20a05d90e7a09c738f67baaf9d8e585057f460c9baadcf", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "6b871417c74e5491db7406c345021bf88a4ea792be89a4e44f2c8136e69b4e5a", "generation_seconds_batch": 25.44541536597535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.074678421020508, "target_z": 1.9218748610504095, "ce": 5.967014789581299, "genuineness": 4.6705241203308105, "identity": 0.7193766236305237, "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_Concentration/16a7638e11fb86925a20a05d90e7a09c738f67baaf9d8e585057f460c9baadcf.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": "16c77897f1da7f3f387cc0ae86a8adbc14c2fbe017cec60ae4ba0fd1d8ee0601", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6c629598cdd7c866cdf918c6c68e7fe01445ed5cba8c352366ed2e032d92e07e", "generation_seconds_batch": 25.30103811796289, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6808488368988037, "target_z": 1.3828125363308563, "ce": 6.372091293334961, "genuineness": 4.519899368286133, "identity": 0.5945842266082764, "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_Concentration/16c77897f1da7f3f387cc0ae86a8adbc14c2fbe017cec60ae4ba0fd1d8ee0601.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "17958fb4191ed8debbfbbf9f94b2b7a2d59b1cdaf8a7b25b15c82f654d36b321", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "22ad58aaa856fbdb0b4c6269e636b48fe44efc3cfbbb789faee1816dc2ebb746", "generation_seconds_batch": 17.55088362901006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6751410961151123, "target_z": 1.3749999490093245, "ce": 6.006728172302246, "genuineness": 4.381826400756836, "identity": 0.6315698027610779, "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_Concentration/17958fb4191ed8debbfbbf9f94b2b7a2d59b1cdaf8a7b25b15c82f654d36b321.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "17e9bf8aeea1ef5a7a7ae79b255d21af1fe2ea0b7a0644f76c98d0314098f277", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2e9c2840b547e1d1d55afec3a5a61d6668500d739924d6a02ad34be6889d8d6a", "generation_seconds_batch": 17.6092372010462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9605250358581543, "target_z": 1.7656250726617124, "ce": 6.078212261199951, "genuineness": 4.519899368286133, "identity": 0.6962420344352722, "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_Concentration/17e9bf8aeea1ef5a7a7ae79b255d21af1fe2ea0b7a0644f76c98d0314098f277.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "187334b60b0634270c1888c18791106a15d4a365b163fec7ca4860e34957e82b", "bucket": "emo_Concentration", "phase": "wording", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "322d821e0248b5f184f10ec874694bef0053c2941e75b9b2db8c13622727a9c5", "generation_seconds_batch": 21.898169263033196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8178329467773438, "target_z": 1.5703123476653573, "ce": 6.1894097328186035, "genuineness": 4.432034492492676, "identity": 0.624741792678833, "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_Concentration/187334b60b0634270c1888c18791106a15d4a365b163fec7ca4860e34957e82b.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "18a1c2d53b0d12b81aba65215cf178ef43a8c19992ce42543951bed90a4324b8", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "592341937957a6efe0d99ff5971e65d6b1b0769a63ceeb66f1bd9a6adadefc79", "generation_seconds_batch": 17.747126223985106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0975091457366943, "target_z": 1.9531248839962134, "ce": 5.935244083404541, "genuineness": 4.231201171875, "identity": 0.6269875764846802, "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_Concentration/18a1c2d53b0d12b81aba65215cf178ef43a8c19992ce42543951bed90a4324b8.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "18b7b1c4e30ef52c389fea0926b21497b51605ca088505ebc1fae95bc7df3e48", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "7e50dc2858eb0ac7d4be54c386eea64ebf976d35a402cd43ecc7332fd803b578", "generation_seconds_batch": 24.00303601101041, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.451385259628296, "target_z": 2.437500076486013, "ce": 6.0146708488464355, "genuineness": 4.306513786315918, "identity": 0.48655247688293457, "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_Concentration/18b7b1c4e30ef52c389fea0926b21497b51605ca088505ebc1fae95bc7df3e48.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "18ebb0c5cad00d1763863bf595c36896c73890c7a51db42805465c95ed0a0559", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "440c75488385de0e71b741efc1a542e8d64cc7e7f28e8e1b9615a7af152fd176", "generation_seconds_batch": 23.7798164220294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6637258529663086, "target_z": 1.359375100706584, "ce": 6.0305562019348145, "genuineness": 4.1998209953308105, "identity": 0.39112943410873413, "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_Concentration/18ebb0c5cad00d1763863bf595c36896c73890c7a51db42805465c95ed0a0559.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "19069238e1ccf1b6eaf3cc89f5991a3c4ae8bd084e6e88f5d629fccc1cab79bb", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "3e0712d844fffe4ee925671bf6595c95e214f6a8e3017f59e906ee0586af09dd", "generation_seconds_batch": 22.267895917990245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8235406875610352, "target_z": 1.5781249349868889, "ce": 6.41180419921875, "genuineness": 4.595211505889893, "identity": 0.33574146032333374, "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_Concentration/19069238e1ccf1b6eaf3cc89f5991a3c4ae8bd084e6e88f5d629fccc1cab79bb.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "19b413dd88f935125e925065335af8d4315c9dc67ec3f451c5be2f2fab276239", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9679beb178aa6aae47c18fc9dec9baedb578b59b22dc290372b02a5bd617605e", "generation_seconds_batch": 25.095981247955933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.880617618560791, "target_z": 1.6562501555215599, "ce": 5.736677646636963, "genuineness": 4.557555198669434, "identity": 0.7088028192520142, "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_Concentration/19b413dd88f935125e925065335af8d4315c9dc67ec3f451c5be2f2fab276239.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "19b68eb951d950d4e8c78cb70766b7560e149931f916772f317ab51e2874a417", "bucket": "emo_Concentration", "phase": "wording", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "f0eaf13f033450ee1c6babf7c92071e17ef5c5fe3d7e77c0bf95489a7bf01c82", "generation_seconds_batch": 21.023034170968458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0689709186553955, "target_z": 1.9140626000692005, "ce": 6.133810997009277, "genuineness": 4.3127899169921875, "identity": 0.5014019012451172, "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_Concentration/19b68eb951d950d4e8c78cb70766b7560e149931f916772f317ab51e2874a417.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "1a79962b12bf17aa0e43bb9e287309f3a8c26829529d23ff4bf5e7eb6cc3a863", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "380d35e4d340b5e98107d102cb8d20df3cfb8534acf246309ffdf910e6b1108e", "generation_seconds_batch": 19.327002711012028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.971940279006958, "target_z": 1.7812499209644532, "ce": 5.764476776123047, "genuineness": 4.570107460021973, "identity": 0.6269358992576599, "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_Concentration/1a79962b12bf17aa0e43bb9e287309f3a8c26829529d23ff4bf5e7eb6cc3a863.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": "1b39b8584989ce317a870ba639bb860b64333d2d2d71ab32ec1c3f401e0ebea4", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e310bff91cc6cf004b453539d11e771a55a3a6c98f10e5ef022f55a7b213ddde", "generation_seconds_batch": 24.009318773052655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.15458607673645, "target_z": 2.0312501045308844, "ce": 5.998785495758057, "genuineness": 4.325342178344727, "identity": 0.5996794700622559, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/1b39b8584989ce317a870ba639bb860b64333d2d2d71ab32ec1c3f401e0ebea4.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "1b49d5448ac4c3226b0c62ae0112116f10e8f1248f03b803bd59d84dc4a3641f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "b2b682bbb1ec56584d78edba3c45a666f9c9a7e59c05ae856b771fd937f721d5", "generation_seconds_batch": 25.213647861033678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.074678421020508, "target_z": 1.9218748610504095, "ce": 6.284721851348877, "genuineness": 3.9927117824554443, "identity": 0.5642719268798828, "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_Concentration/1b49d5448ac4c3226b0c62ae0112116f10e8f1248f03b803bd59d84dc4a3641f.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "1baac2a093c04c36e0a25691faed531e49c8c80572795b354ea8df3928043fce", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "344430b650f42aa4adfada4212272ac3641ae9a05431c338156439b0c7fa460e", "generation_seconds_batch": 22.12301750201732, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.36006236076355, "target_z": 2.3124999847027974, "ce": 6.046441555023193, "genuineness": 4.400654315948486, "identity": 0.6047196388244629, "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_Concentration/1baac2a093c04c36e0a25691faed531e49c8c80572795b354ea8df3928043fce.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "1c12938f35044545da25657bd66ae24620e4c358989416757952d5f8d0683aa2", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "ac5465108e422299c5803c8c82baa815f49856efc623000b688d05a9a35eea2c", "generation_seconds_batch": 22.26029272004962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.732217788696289, "target_z": 1.4531248432036732, "ce": 6.133810997009277, "genuineness": 4.632867813110352, "identity": 0.2308354675769806, "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_Concentration/1c12938f35044545da25657bd66ae24620e4c358989416757952d5f8d0683aa2.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "1c6a93178b937bed0fcdee9761098e87ec150ddc8eca5e8ad5cf89d585519936", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "7c2598280f2ef71aaa33727ecbb7c6a9d36da59934efc4671271ee2524a61377", "generation_seconds_batch": 23.455929919029586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9947710037231445, "target_z": 1.8124999439102571, "ce": 6.09409761428833, "genuineness": 4.306513786315918, "identity": 0.517338216304779, "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_Concentration/1c6a93178b937bed0fcdee9761098e87ec150ddc8eca5e8ad5cf89d585519936.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "1caa8370c47210b0ec97bbde16b1eed1038ba23b376fac7332bd530b63c62ddd", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d3208406c56eb1071d60f1e359fdffcabe7531efdbf93b6343c7325d908e3f2e", "generation_seconds_batch": 23.411467954982072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.211662769317627, "target_z": 2.109374998725233, "ce": 5.935244083404541, "genuineness": 4.042920112609863, "identity": 0.3758408725261688, "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_Concentration/1caa8370c47210b0ec97bbde16b1eed1038ba23b376fac7332bd530b63c62ddd.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "1d1933a805fba8e3fb4417d9b4e4c1ce1526953a7263e0e30c289b30d4c67f09", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "22a4c68405a534c9ecd9f2ce2c8f7b501d13ac5e5c71cec17b28d901b9a9201c", "generation_seconds_batch": 23.53221224306617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3583650588989258, "target_z": 0.9414062477691579, "ce": 6.197352409362793, "genuineness": 4.532451152801514, "identity": 0.5718603730201721, "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_Concentration/1d1933a805fba8e3fb4417d9b4e4c1ce1526953a7263e0e30c289b30d4c67f09.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "1d32cbf82caa3fd6701d7305f0e933580d27433361b973e4dafda4a62bf956ad", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "a7f9d60929e8a96505df8a8fbe590da59f7d27d4f766e3d9ae9a8534de3c1e28", "generation_seconds_batch": 23.354489612975158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0975091457366943, "target_z": 1.9531248839962134, "ce": 6.078212261199951, "genuineness": 4.118232727050781, "identity": 0.6788597106933594, "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_Concentration/1d32cbf82caa3fd6701d7305f0e933580d27433361b973e4dafda4a62bf956ad.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "ab4fc2994e1c000ce663cc9eb4a37f59d4948863075170987894610771559a22", "generation_seconds_batch": 19.688710921094753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.15458607673645, "target_z": 2.0312501045308844, "ce": 6.165581703186035, "genuineness": 4.344170093536377, "identity": 0.5945942997932434, "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_Concentration/1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3.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": "1d609947e833220968aeac9eb7da6dbbe7feadb9265dae0dbf2e8802468a25f4", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4f513509edc22f18facfdf678ded9744c9aa98cc34f8099a4432b7bab0fc730c", "generation_seconds_batch": 18.415697338059545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.777879238128662, "target_z": 1.515624889095281, "ce": 6.054384231567383, "genuineness": 4.507347106933594, "identity": 0.7662621736526489, "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_Concentration/1d609947e833220968aeac9eb7da6dbbe7feadb9265dae0dbf2e8802468a25f4.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "0c8b8fb727bf1a79203ea2c03c7facf3da7b639fbc4fe25112565a56e94aa344", "generation_seconds_batch": 18.137304752948694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.777879238128662, "target_z": 1.515624889095281, "ce": 6.2767791748046875, "genuineness": 4.632867813110352, "identity": 0.7511486411094666, "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_Concentration/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "1e1aa39c021f39526d16d934c5e79aa94f366509166ffd28ca0eb6018b1e1dc6", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "8dc04c55595d707ec0e9ad637cfafcce9dc5878bb052fe6de2949f0ee8bee058", "generation_seconds_batch": 22.13549752801191, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8121254444122314, "target_z": 1.562500086684148, "ce": 6.221180438995361, "genuineness": 4.268857479095459, "identity": 0.6514080762863159, "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_Concentration/1e1aa39c021f39526d16d934c5e79aa94f366509166ffd28ca0eb6018b1e1dc6.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": "1e71e26b86969a10c8e1709131dabf10b3db70db582d782c0b514f3b7108f650", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "903ec6b0343955b27fddce9fc35d6ed155abd6de34f973f847c97e87ccd1f9d3", "generation_seconds_batch": 14.543022187892348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6112000942230225, "target_z": 2.6562499107663182, "ce": 6.022613525390625, "genuineness": 4.256305694580078, "identity": 0.6558235883712769, "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_Concentration/1e71e26b86969a10c8e1709131dabf10b3db70db582d782c0b514f3b7108f650.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": "1ea1e031be83567764d13b645570ce8076ee009966bb62d44706e827f9c5b7b9", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "c71a4f88788a0e5f40f03c664083d63d98058c10b5458c86d646f216424d5532", "generation_seconds_batch": 23.083371161017567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.209965467453003, "target_z": 0.7382812617915937, "ce": 6.221180438995361, "genuineness": 4.6203155517578125, "identity": 0.6087502837181091, "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": 0.120000000000001, "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_Concentration/1ea1e031be83567764d13b645570ce8076ee009966bb62d44706e827f9c5b7b9.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "924663522e42e79a412408358a59294691cc92d5770cf2674d02b9e532a06d6a", "generation_seconds_batch": 19.688710921094753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1774168014526367, "target_z": 2.0625001274766883, "ce": 6.316492557525635, "genuineness": 4.519899368286133, "identity": 0.7019695043563843, "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_Concentration/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "1f30ffcdc498fad352c4c2b0f04b7062059e1e53104376f059c636ac4c77b378", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "20ad8b07e3c9cd313db6e97536fe3bb37800b6d57bd9e3a47231c1d86a590ce2", "generation_seconds_batch": 23.787033897941, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1317553520202637, "target_z": 2.0000000815850805, "ce": 6.1894097328186035, "genuineness": 4.419482707977295, "identity": 0.6631704568862915, "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_Concentration/1f30ffcdc498fad352c4c2b0f04b7062059e1e53104376f059c636ac4c77b378.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "1f49bdf519c944e77b98242021d50eb04af3cef38fc6f5278096d6d5c2804c21", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "74a5cbf72dc5318792879f12c68b97e2a4e6be081c8474e72152912322009ab6", "generation_seconds_batch": 23.728397047962062, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3258163928985596, "target_z": 2.2656251134542527, "ce": 5.831989288330078, "genuineness": 3.9550557136535645, "identity": 0.7394256591796875, "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_Concentration/1f49bdf519c944e77b98242021d50eb04af3cef38fc6f5278096d6d5c2804c21.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "1f82387e4ec6b74800823afc2fca3a1abfd6a9d0317b612b6616a946af817791", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "b6497557c5196094aeb6676ec055e456110ad5d7bb94feefb232db28af95a914", "generation_seconds_batch": 23.858950015041046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.834956169128418, "target_z": 1.593750109629952, "ce": 5.6334228515625, "genuineness": 4.519899368286133, "identity": 0.6328521966934204, "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_Concentration/1f82387e4ec6b74800823afc2fca3a1abfd6a9d0317b612b6616a946af817791.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": "20498b75f9d786d5b2795cd9974d335c14ef93f898f1b7510bff3c79c47bef99", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "49b06f109b7bc0d62c32c7ad8047c16b5ff87d86af77bb7ccf5f735f68b68f5a", "generation_seconds_batch": 17.36695839499589, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.017601728439331, "target_z": 1.843749966856061, "ce": 5.681078910827637, "genuineness": 4.519899368286133, "identity": 0.6169737577438354, "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_Concentration/20498b75f9d786d5b2795cd9974d335c14ef93f898f1b7510bff3c79c47bef99.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "20c79b61a593d517cd4cd56ff50411b2ff2fb98c4ef2df1d0336335e5b1934b1", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "3cafa7ac7862aa3bab0abf3be3eb88444ba73ff559e0923ccb744c44115f57ae", "generation_seconds_batch": 17.250885035959072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.36006236076355, "target_z": 2.3124999847027974, "ce": 6.125868320465088, "genuineness": 4.595211505889893, "identity": 0.6975239515304565, "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_Concentration/20c79b61a593d517cd4cd56ff50411b2ff2fb98c4ef2df1d0336335e5b1934b1.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "211f59488412d1fc2e3f37ee7761e80e5f3b261ce76c7c6e5f3c532c66e266b8", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "1323633b9afba36c373fd7549d2ae4f9cf6e8a66633cbc720bca19f80850ca56", "generation_seconds_batch": 16.74613463296555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4810800552368164, "target_z": 1.1093749171401526, "ce": 6.221180438995361, "genuineness": 4.444586753845215, "identity": 0.22746770083904266, "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_Concentration/211f59488412d1fc2e3f37ee7761e80e5f3b261ce76c7c6e5f3c532c66e266b8.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": "2124147d32001aac8978ae962a69c87ddb1bc1d2c90ba6eb2cee12152c5b2832", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "e8b1f12dc72e3ef6c9e4dede646bab2213c40c668bfca36426c96e66ba303c85", "generation_seconds_batch": 17.668448198004626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.725353717803955, "target_z": 2.812500025495338, "ce": 5.998785495758057, "genuineness": 4.356721878051758, "identity": 0.7960497140884399, "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_Concentration/2124147d32001aac8978ae962a69c87ddb1bc1d2c90ba6eb2cee12152c5b2832.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": "216ba45fc511f492a7518585f3e0c256f086c3d97c1ce5d0319330a0389dbb09", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "24216e026a60a7606a8e35d4a2c0c13eccd2dcad31511e3160ad05a378479147", "generation_seconds_batch": 15.188658368075266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5381568670272827, "target_z": 1.1874999745046624, "ce": 6.157639026641846, "genuineness": 4.243753433227539, "identity": 0.7526016235351562, "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_Concentration/216ba45fc511f492a7518585f3e0c256f086c3d97c1ce5d0319330a0389dbb09.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "2178b0b85bf252f0ae6958539358c8fadaae47e7f1ef49a301a3abeb87c487f4", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "4902c682c17866efce476881f0f1a87bb1683f90fa2375c6824ed837857b65ef", "generation_seconds_batch": 18.951957929995842, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7664639949798584, "target_z": 1.5000000407925402, "ce": 5.9431867599487305, "genuineness": 4.356721878051758, "identity": 0.5942631959915161, "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_Concentration/2178b0b85bf252f0ae6958539358c8fadaae47e7f1ef49a301a3abeb87c487f4.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "21904d359df6258385a1239bc010eb8df78317b7072367e98d565b41eb2d4f34", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "b18587b7a235d2e262d9a34eea44b1f4c4fd7d1aad9965695277c92c73b9556e", "generation_seconds_batch": 25.213647861033678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9947710037231445, "target_z": 1.8124999439102571, "ce": 6.221180438995361, "genuineness": 4.507347106933594, "identity": 0.7109190821647644, "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_Concentration/21904d359df6258385a1239bc010eb8df78317b7072367e98d565b41eb2d4f34.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "21dc7150bf28b00c55b938f8f37cc0241236d29b4d43838c40ed11e2d98e39cc", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "8144de1e1862d5b67541dbd947b4426158a047c22e29decafc7698bd19f5d45c", "generation_seconds_batch": 22.94649548199959, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1431705951690674, "target_z": 2.0156249298878213, "ce": 6.348263263702393, "genuineness": 4.137060642242432, "identity": 0.4469192922115326, "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_Concentration/21dc7150bf28b00c55b938f8f37cc0241236d29b4d43838c40ed11e2d98e39cc.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "21fb800751ce12bf0ad22a40b542eff9a94aa052e9f905ab46f96675fb04df21", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d26de8bec7ab717fe8a1d36432d3ab9bffc82bb14919b8483ad09f4bf4c766b9", "generation_seconds_batch": 24.00303601101041, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.245908737182617, "target_z": 2.1562498699737778, "ce": 5.736677646636963, "genuineness": 4.419482707977295, "identity": 0.4165555238723755, "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_Concentration/21fb800751ce12bf0ad22a40b542eff9a94aa052e9f905ab46f96675fb04df21.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "228a256559bd2d646d565e1a9677b24f2a6322f23649811d08bd130d13835e8f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "6935b921e8c3b0aa52c92b87a7f15d0fa0f54f873c273e10122b929a85c47b0a", "generation_seconds_batch": 22.33602329203859, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2527730464935303, "target_z": 0.7968750140224358, "ce": 5.299830436706543, "genuineness": 4.394378662109375, "identity": 0.6868350505828857, "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_Concentration/228a256559bd2d646d565e1a9677b24f2a6322f23649811d08bd130d13835e8f.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "229bcc10743a1baa2350a37dc29874b8938aae465fd835de467f103c0ecebd18", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "098c37e4efc14409491ddaeb2393f2053b0475ac810c6b8e428e6b8289c3858b", "generation_seconds_batch": 23.711970569915138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9947710037231445, "target_z": 1.8124999439102571, "ce": 6.197352409362793, "genuineness": 4.250029563903809, "identity": 0.5432702302932739, "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_Concentration/229bcc10743a1baa2350a37dc29874b8938aae465fd835de467f103c0ecebd18.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "22ba1ffff980b7d2b61280f9e9b57b5227f72cf9bb197b7522dd81ee6916e98c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "b209e350f15fe0888b1f80d22fe1a23e234735a594b495a3fe21d5577969f42d", "generation_seconds_batch": 18.254987535998225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.485631227493286, "target_z": 2.484374947734558, "ce": 6.086154937744141, "genuineness": 4.042920112609863, "identity": 0.7932538986206055, "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_Concentration/22ba1ffff980b7d2b61280f9e9b57b5227f72cf9bb197b7522dd81ee6916e98c.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "22cb0f10aede73e0e4e21ea2542535c9deb7c0d52acb009288f09b67216623b8", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "1eca4614f283c274c3e74b2292468a2c1a2815678dd9df7fd5158b732959ef00", "generation_seconds_batch": 24.003468755050562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4171390533447266, "target_z": 2.390624878897146, "ce": 5.911416053771973, "genuineness": 4.18099308013916, "identity": 0.6677249670028687, "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_Concentration/22cb0f10aede73e0e4e21ea2542535c9deb7c0d52acb009288f09b67216623b8.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": "23097702cab8c05732ad09e24669ba95993ffd3fa9de8f7b8eefc8aa4b0b8365", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "8470c349f6418eb8caf2bee40de20e3671769e9dd8540133c29afca6ebf8d3ee", "generation_seconds_batch": 16.822206430020742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2230780124664307, "target_z": 2.124999847027974, "ce": 6.09409761428833, "genuineness": 4.519899368286133, "identity": 0.75702965259552, "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_Concentration/23097702cab8c05732ad09e24669ba95993ffd3fa9de8f7b8eefc8aa4b0b8365.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "230efa3fd3e27e831b486e2a2817bf8344922bfce66f591289e4c15741e9734c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d18143fba55058bfbd8e16661d18a03f034a364b86eb1c511cd9ad728c8298e8", "generation_seconds_batch": 22.018248251988553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9987814426422119, "target_z": 0.44921879429814926, "ce": 5.998785495758057, "genuineness": 4.231201171875, "identity": 0.16704370081424713, "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_Concentration/230efa3fd3e27e831b486e2a2817bf8344922bfce66f591289e4c15741e9734c.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "232da0f774aaf3058595164c4f0e7a1e415d6b3a2e739a669668a179e7c75e7d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d6317f801e4fe979b4b6d4b958277653c1dd7973822a34286db00d06a665d496", "generation_seconds_batch": 22.83976077195257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6694334745407104, "target_z": 1.3671875248579544, "ce": 6.252951145172119, "genuineness": 4.005263805389404, "identity": 0.3815740942955017, "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_Concentration/232da0f774aaf3058595164c4f0e7a1e415d6b3a2e739a669668a179e7c75e7d.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "2337088d490bf09b965e3357c573011229a240a882bf90eac4ecce729668114d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "7f9a130e27ff9d76b5150bdb52071b797ab694486a957b64ee259c0c3c5634e2", "generation_seconds_batch": 16.097398016951047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7093873023986816, "target_z": 1.4218751465981918, "ce": 6.324435234069824, "genuineness": 4.331617832183838, "identity": 0.6400395035743713, "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_Concentration/2337088d490bf09b965e3357c573011229a240a882bf90eac4ecce729668114d.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": "2352df4e2dc5ffedc3f20c4b5dd05aea7977a5bcbefc3cc04a200d4e330766f7", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9cb43319439dece3a3f55641fc5f565e54cf4b4fc2ac890e432186360d559338", "generation_seconds_batch": 24.995299836969934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9833557605743408, "target_z": 1.7968750956075163, "ce": 6.1020402908325195, "genuineness": 4.582659721374512, "identity": 0.7069145441055298, "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_Concentration/2352df4e2dc5ffedc3f20c4b5dd05aea7977a5bcbefc3cc04a200d4e330766f7.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "23a4c4f5b2f6e5b2cca72613377c16e2d377ddba7a42dd2347b70683113e6bf0", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "1f300b99959de2fb1d37b45765c95bfaa4c968ff354e30123c4b7ad4d3198449", "generation_seconds_batch": 24.979078728007153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5210338830947876, "target_z": 1.16406253888039, "ce": 6.332377910614014, "genuineness": 4.444586753845215, "identity": 0.44478854537010193, "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_Concentration/23a4c4f5b2f6e5b2cca72613377c16e2d377ddba7a42dd2347b70683113e6bf0.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "23dd403a264839834e44cbb3c708c96dd15da611fe24a51c12e553f4d94d5c12", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "eb204e68593f1f3c460f95ee63f7cea96124ac503a5b7ca0dcc8fd7bb1b3a3b7", "generation_seconds_batch": 16.097398016951047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7950024604797363, "target_z": 1.539062651059876, "ce": 6.133810997009277, "genuineness": 4.375550270080566, "identity": 0.7149611711502075, "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_Concentration/23dd403a264839834e44cbb3c708c96dd15da611fe24a51c12e553f4d94d5c12.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": "23fd15654f63a67e3028da0ebe9d6bab609c64c27b1548a7a08b7e627247bb60", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "238fa2f41f7814793d92ca8219f326a52b8828f835be147d2b73b2c29f1cd19c", "generation_seconds_batch": 17.619504275964573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6979718208312988, "target_z": 1.4062499719551285, "ce": 6.419747352600098, "genuineness": 4.507347106933594, "identity": 0.273256778717041, "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_Concentration/23fd15654f63a67e3028da0ebe9d6bab609c64c27b1548a7a08b7e627247bb60.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "2407c3971b4b8966bd54fd6da727e29300e003a53fb5fa5467b9bbf399bdddca", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9bed0fa490e3ee32f91ba5d10593031157d64cd156406edcdec828ae93b32b8a", "generation_seconds_batch": 23.751405931892805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1431705951690674, "target_z": 2.0156249298878213, "ce": 6.284721851348877, "genuineness": 4.250029563903809, "identity": 0.5932272672653198, "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_Concentration/2407c3971b4b8966bd54fd6da727e29300e003a53fb5fa5467b9bbf399bdddca.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": "24195b86538fc8f76513e4c547cdd7bfe97adb7e287dd8b562ecb89123c4a2c4", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce60105518b1e76f49cfc1d36f9b8d1a416946693c2b9384a236c3987bdebcec", "generation_seconds_batch": 23.854426486999728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.074678421020508, "target_z": 1.9218748610504095, "ce": 6.284721851348877, "genuineness": 4.519899368286133, "identity": 0.5633547306060791, "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_Concentration/24195b86538fc8f76513e4c547cdd7bfe97adb7e287dd8b562ecb89123c4a2c4.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": "24a339a9c9183681521aaca9b65a2f9c6ab2d757c6994490eb1be0abbffc9846", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c9709c35371d8c75597f2216b33d679a824200e251d1723b3742b071ae6aa43", "generation_seconds_batch": 17.395528740016744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7036795616149902, "target_z": 1.4140625592766602, "ce": 6.24500846862793, "genuineness": 4.482243061065674, "identity": 0.9009132385253906, "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_Concentration/24a339a9c9183681521aaca9b65a2f9c6ab2d757c6994490eb1be0abbffc9846.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "24a3a973c865525d21fa35e77849d8669131b468ce43059dd303b6ca91eee859", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d833dae667167a5ad2b9de8e10db0b112104ed2af325858a1f254d7891a25de4", "generation_seconds_batch": 23.457595338928513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.127204179763794, "target_z": 0.6250000509906753, "ce": 6.205295085906982, "genuineness": 4.20609712600708, "identity": 0.384695827960968, "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_Concentration/24a3a973c865525d21fa35e77849d8669131b468ce43059dd303b6ca91eee859.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "24c15af39be4f28e3508fdd786689879d8fedec59d14c377e1c363c1e15dc99d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8c1603374b8f56713e15a7d44806f4ca7821d51bb9f034332508479226686416", "generation_seconds_batch": 24.717872282955796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.063263177871704, "target_z": 1.906250012747669, "ce": 6.1020402908325195, "genuineness": 3.9801597595214844, "identity": 0.18963760137557983, "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_Concentration/24c15af39be4f28e3508fdd786689879d8fedec59d14c377e1c363c1e15dc99d.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "24cdd3d63b6c1da2b97669dcc2acee2d18e294c33c1e3665df800c5dd8aa22ca", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "8be236dd5402d450596d76da600b119eeba5fc538c3312c669c09bd69c34cb39", "generation_seconds_batch": 24.821697078994475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.120339870452881, "target_z": 1.9843749069420173, "ce": 5.518253803253174, "genuineness": 4.381826400756836, "identity": 0.8137845993041992, "hypothesis": "J'ai trouvé la petite boîte.", "wer": 0.7368421052631579, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/24cdd3d63b6c1da2b97669dcc2acee2d18e294c33c1e3665df800c5dd8aa22ca.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "24d32b10a018cad9ae53a782e76d0205f48da61c3727b536f12012abb8d0712c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "b7e3a68d2748514bb2750927534ad8dfd67400fac271666267d3ce06608e6daa", "generation_seconds_batch": 24.452369373990223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5609875917434692, "target_z": 1.2187499974504663, "ce": 5.772419452667236, "genuineness": 4.570107460021973, "identity": 0.5625435709953308, "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_Concentration/24d32b10a018cad9ae53a782e76d0205f48da61c3727b536f12012abb8d0712c.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "25e4c0aa83ba6dccff89debe8ad05ed9c1f76a19d843119db3383bb946856a41", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9ff2d054a96a8ea99f3f20c161bc2a302c7a6132237d1153357811fffb66baac", "generation_seconds_batch": 16.74613463296555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6294796466827393, "target_z": 1.3124999031177167, "ce": 6.149696350097656, "genuineness": 3.7918784618377686, "identity": 0.41755127906799316, "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_Concentration/25e4c0aa83ba6dccff89debe8ad05ed9c1f76a19d843119db3383bb946856a41.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "268ecb2f14e9862b025470dccf88948c7a9227cd76758bf9a8da04519d00b815", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "8db9a3251059d398bbca22e28cdc58305cc706966c9ba4e32e0814b84653cc74", "generation_seconds_batch": 23.59407083305996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4240033626556396, "target_z": 1.031250022945804, "ce": 6.4515180587768555, "genuineness": 4.413206577301025, "identity": 0.2162548005580902, "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_Concentration/268ecb2f14e9862b025470dccf88948c7a9227cd76758bf9a8da04519d00b815.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "269595da24a614fe6e73456f5dda545503496984b2b8225401f41c00fdeccffb", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "24b7808d6692c24ef70249b631ea6893f03f2b21c8f70da5ff32a95f6b9e3b39", "generation_seconds_batch": 17.423174479976296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.646602749824524, "target_z": 1.3359375019121504, "ce": 6.300607204437256, "genuineness": 4.281409740447998, "identity": 0.5006069540977478, "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_Concentration/269595da24a614fe6e73456f5dda545503496984b2b8225401f41c00fdeccffb.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "269c7c7bf337b4dc27e3880e6959878a1ea79d19a91e4e7a010f84eca339a465", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "677337380c02d4af623b17b92e2b068665ff28cdc15ff28fc6b13b3bbb53f71a", "generation_seconds_batch": 24.050950662000105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0518476963043213, "target_z": 1.8906248381046056, "ce": 6.078212261199951, "genuineness": 4.331617832183838, "identity": 0.7038407325744629, "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_Concentration/269c7c7bf337b4dc27e3880e6959878a1ea79d19a91e4e7a010f84eca339a465.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "26c355bcd27d57f2b49e08e0810c0dc4dca6a87245bc3a5ac451c8b46092d642", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "43f87ccc6c0392d18bc45b7667643631087defd4cd47da75850d9385bf700a69", "generation_seconds_batch": 24.2953409019392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1243503093719482, "target_z": 0.6210937573299096, "ce": 6.213237762451172, "genuineness": 4.482243061065674, "identity": 0.4615739583969116, "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_Concentration/26c355bcd27d57f2b49e08e0810c0dc4dca6a87245bc3a5ac451c8b46092d642.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": 128, "seconds_generated": 10.24, "mp3_sha256": "9e849b5cc88510b61a0eef7918069b118976afc75bf289a6149acbb67e0ba534", "generation_seconds_batch": 17.74098897597287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5267415046691895, "target_z": 1.1718749630317604, "ce": 6.475345611572266, "genuineness": 4.457139015197754, "identity": 0.32872113585472107, "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_Concentration/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "26d7d50a7912cc695c6446783dc214c1fcd86a2f04758855757079b7fe76fffd", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "687d6714c3d09af29eef106948cae4d5ec32ed3ec2c8898b20751d2de6493b6a", "generation_seconds_batch": 18.010416439035907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6523103713989258, "target_z": 1.3437499260635206, "ce": 6.38797664642334, "genuineness": 4.287685871124268, "identity": 0.35324451327323914, "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_Concentration/26d7d50a7912cc695c6446783dc214c1fcd86a2f04758855757079b7fe76fffd.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "26ee80d30535baca35f27eb8e2db371d15086c1decbcc4fc79af1011244cface", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "975a7bf321e51f20b085e8df961da9fad4f00605a31b031805aeeb69ce0e3933", "generation_seconds_batch": 17.285535609000362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9376943111419678, "target_z": 1.7343750497159085, "ce": 5.25614595413208, "genuineness": 4.268857479095459, "identity": 0.6559469699859619, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás linda.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/26ee80d30535baca35f27eb8e2db371d15086c1decbcc4fc79af1011244cface.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "271e3fe91d4ddfda99b7923b3a8e44537b5826cdd007a4dd4ec5fc3e1c09b5a9", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "a3b92ae2aed0352cd95c173ba223948565733d4ff9a3b4a08116af535912a513", "generation_seconds_batch": 23.60238571697846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.017601728439331, "target_z": 1.843749966856061, "ce": 5.847874641418457, "genuineness": 4.444586753845215, "identity": 0.6998125314712524, "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_Concentration/271e3fe91d4ddfda99b7923b3a8e44537b5826cdd007a4dd4ec5fc3e1c09b5a9.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "272edffae2027eecb092a4b74931b5715fb04295aee9db10c90bf5ffb6e82636", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "79d7b4468dfffee1c7926f762430cc08cdb9c9ad14230530224f42810fbb1aaf", "generation_seconds_batch": 23.928716331953183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0975091457366943, "target_z": 1.9531248839962134, "ce": 6.09409761428833, "genuineness": 4.369274139404297, "identity": 0.6613483428955078, "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_Concentration/272edffae2027eecb092a4b74931b5715fb04295aee9db10c90bf5ffb6e82636.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": "2736c14465bb73eeeed382cc17cfd54d6a4bb0ca18ea2bbb6f38b4b7ee8d96a4", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "45be623b4fcdfc49a73dde9f655118bab98c0d93f7948d6647d1ae1bc1f8f86f", "generation_seconds_batch": 26.316047413973138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9833557605743408, "target_z": 1.7968750956075163, "ce": 6.395919322967529, "genuineness": 4.162164688110352, "identity": 0.3168450593948364, "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_Concentration/2736c14465bb73eeeed382cc17cfd54d6a4bb0ca18ea2bbb6f38b4b7ee8d96a4.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "276f8da09a89b88f16a4ed08a110057b9321e22a1d7e7377a28de4414f0235e2", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "a5c022b3279cb2df8b67c96b1e4485c84c32af379147e6fd8d57afb6e9847f5c", "generation_seconds_batch": 17.087197503075004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7493410110473633, "target_z": 1.476562605168268, "ce": 5.967014789581299, "genuineness": 4.632867813110352, "identity": 0.6343427896499634, "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_Concentration/276f8da09a89b88f16a4ed08a110057b9321e22a1d7e7377a28de4414f0235e2.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "27d0e0471cb9fff1dd97e5d9c79f122a61bf6963aced90924e8e18f08389f264", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "c673db8a378ac530c5e7d65840fce8c5e769d156e153cc5e3da7c6efea63e603", "generation_seconds_batch": 23.15741673100274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7436332702636719, "target_z": 1.4687500178467363, "ce": 6.006728172302246, "genuineness": 4.595211505889893, "identity": 0.6698312163352966, "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_Concentration/27d0e0471cb9fff1dd97e5d9c79f122a61bf6963aced90924e8e18f08389f264.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "27dd1634dc0f8734bc6c7b9c75cb434d050a5c4d024f63ca0f88499549a5247d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d5c453711c5037113e2b9746837a7c9aadfeeb2b3f3abc73b80e497ec32c8dcd", "generation_seconds_batch": 23.538102542050183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2230780124664307, "target_z": 2.124999847027974, "ce": 6.109982967376709, "genuineness": 4.193545341491699, "identity": 0.7939234972000122, "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_Concentration/27dd1634dc0f8734bc6c7b9c75cb434d050a5c4d024f63ca0f88499549a5247d.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "2801b571e6b67e83129516bdce640986029f0ea1f6df4d1adc5375e43c2c41c8", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "9312e634d49bc1d233d26c9ce0462ff15af0b6e2f0bb2dad25d5a4eb25119dcf", "generation_seconds_batch": 18.136188503005542, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.15458607673645, "target_z": 2.0312501045308844, "ce": 5.959072113037109, "genuineness": 4.8588056564331055, "identity": 0.7615283727645874, "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_Concentration/2801b571e6b67e83129516bdce640986029f0ea1f6df4d1adc5375e43c2c41c8.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": "2813c91421f7efafb9b4256ea94752d7e4d2da7db9dc9ad21bec1d460bb71166", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b66bc5b4d60089bd186ebe69280d8fe9020f06c171216956ed55c7c674a3786e", "generation_seconds_batch": 23.436851065955125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.80641770362854, "target_z": 1.5546874993626165, "ce": 6.229123115539551, "genuineness": 4.21237325668335, "identity": 0.6023919582366943, "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_Concentration/2813c91421f7efafb9b4256ea94752d7e4d2da7db9dc9ad21bec1d460bb71166.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "2829bf524a015fd07838362b1b48d4b77a026688fd5f6e03b5e152bc56301f4c", "bucket": "emo_Concentration", "phase": "wording", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "09d83cf163bc8d236233325e1485314226edd3c38bdf6836abec0fdc0a2eeee5", "generation_seconds_batch": 21.023034170968458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.302985668182373, "target_z": 2.2343750905084487, "ce": 5.8875885009765625, "genuineness": 4.005263805389404, "identity": 0.72007155418396, "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_Concentration/2829bf524a015fd07838362b1b48d4b77a026688fd5f6e03b5e152bc56301f4c.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": "290af756c744b6bb805903ab860bae6a6b5d6404fa9d322016997af61623c717", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "0f0780c90a038a712a68c29798934a427b613235e23d2ef600df3acc08788e08", "generation_seconds_batch": 17.36695839499589, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2002475261688232, "target_z": 2.0937501504224922, "ce": 6.141753673553467, "genuineness": 4.400654315948486, "identity": 0.5823073983192444, "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_Concentration/290af756c744b6bb805903ab860bae6a6b5d6404fa9d322016997af61623c717.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": "29314672a170293392bec3a96aaf537c13efc7be4edae7846f81626621be8381", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "d2711da7ff430ecbaec1196d6ea9cc37ed9fb12f12db5a75389de8b0a3cc9c26", "generation_seconds_batch": 17.241669429000467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.245908737182617, "target_z": 2.1562498699737778, "ce": 6.300607204437256, "genuineness": 4.168440818786621, "identity": 0.3277353048324585, "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_Concentration/29314672a170293392bec3a96aaf537c13efc7be4edae7846f81626621be8381.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": "2958c5d0d18aa3464c1b9146cd0df5d5d2ab5703d5fe87e1b832c573a64f5b5c", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "26c855cfb4e7f2abfb2ff87cd60ba9821149f8ec5654a501e62aaf48be554aee", "generation_seconds_batch": 17.49944514897652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6637258529663086, "target_z": 1.359375100706584, "ce": 5.855817794799805, "genuineness": 4.356721878051758, "identity": 0.868236780166626, "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_Concentration/2958c5d0d18aa3464c1b9146cd0df5d5d2ab5703d5fe87e1b832c573a64f5b5c.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": "29e49de2da93ff3bc6f797e8bf93ea251af6270e2152aaf415133461e589d985", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "744c09dda37a5880e4ade4e26eb38ca94b7825e402d6d56b7ccc37351c429196", "generation_seconds_batch": 18.32915610296186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5153262615203857, "target_z": 1.1562501147290196, "ce": 6.117925643920898, "genuineness": 4.494794845581055, "identity": 0.7393851280212402, "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_Concentration/29e49de2da93ff3bc6f797e8bf93ea251af6270e2152aaf415133461e589d985.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "2a574988f06c25b288570f1bbbd23ebf63d141ce7ee154a65f5361791fe94c70", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "c198451fcf3011b9932eca36a49ebc757fd8ff6631b518b5b82f495c6bfa3a5c", "generation_seconds_batch": 23.378940987982787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.595233678817749, "target_z": 1.2656250318691722, "ce": 5.518253803253174, "genuineness": 4.218649387359619, "identity": 0.5244964957237244, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo está.", "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_Concentration/2a574988f06c25b288570f1bbbd23ebf63d141ce7ee154a65f5361791fe94c70.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "2a745967bf1170ba095c6ba7b1c84131b46012548ea4c8825a72f88fae13e603", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "929c5bcd4f38de71144bbb111b21003e52674c026cd548286ef1d2d90528bd12", "generation_seconds_batch": 24.03718310210388, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.634030818939209, "target_z": 2.687499933712122, "ce": 5.669164657592773, "genuineness": 4.432034492492676, "identity": 0.5693469643592834, "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_Concentration/2a745967bf1170ba095c6ba7b1c84131b46012548ea4c8825a72f88fae13e603.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "2ac4f4891e44987c5b3184aadc39ebfca840a721f177b7a46fc5be08e4f60a0c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "13e97c092a502bc219944035803d65fa5cd279c8f11ac333e83c83327167bfc8", "generation_seconds_batch": 24.78633777203504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.852079153060913, "target_z": 1.6171875452542244, "ce": 5.998785495758057, "genuineness": 4.6956281661987305, "identity": 0.2708887457847595, "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_Concentration/2ac4f4891e44987c5b3184aadc39ebfca840a721f177b7a46fc5be08e4f60a0c.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "2ad30868c4f8e7ca2cd027701eb5cc75280750f1f97e23eb088f500c0181d7b1", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "c42b92c7e0e8c3456361f2c45951a24a21870ea3a2da905f0c569b9b43361cff", "generation_seconds_batch": 23.153470827033743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.578110694885254, "target_z": 1.2421875962448998, "ce": 6.117925643920898, "genuineness": 4.293961524963379, "identity": 0.5256562232971191, "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_Concentration/2ad30868c4f8e7ca2cd027701eb5cc75280750f1f97e23eb088f500c0181d7b1.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "2b33780c880c4d6bfff86f4bbcc36cc591b3f44227fb1a8c53d1cbc9402bff12", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "02a454a7adb796e9cdc4a57f7dd9c8bdf8e1dd9115ad95e9347c5ce0f62621bb", "generation_seconds_batch": 18.099706332897767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6694334745407104, "target_z": 1.3671875248579544, "ce": 5.470598220825195, "genuineness": 4.65797233581543, "identity": 0.5542290806770325, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos la.", "wer": 0.23529411764705882, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/2b33780c880c4d6bfff86f4bbcc36cc591b3f44227fb1a8c53d1cbc9402bff12.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "2b6252027cb32460e0a0893d6cb0a36c98ec31c358db2496e6e053a79a8c8d33", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "932aaa7b09d5673efcd2cc028adb6c42f6c29ae2b1876f8355935cafba2a4d16", "generation_seconds_batch": 22.289799010031857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.302985668182373, "target_z": 2.2343750905084487, "ce": 5.871703147888184, "genuineness": 4.375550270080566, "identity": 0.6607472896575928, "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_Concentration/2b6252027cb32460e0a0893d6cb0a36c98ec31c358db2496e6e053a79a8c8d33.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "2b7c3bc94f51cb9759824cdc2a282ea855393cfb79f1b54bfd14e34a6949d581", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "dabca70af06330321131ae75236370f4b5253fc410cc349c2193571566013f65", "generation_seconds_batch": 22.9003998930566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8121254444122314, "target_z": 1.562500086684148, "ce": 5.824047088623047, "genuineness": 4.68307638168335, "identity": 0.8151177167892456, "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_Concentration/2b7c3bc94f51cb9759824cdc2a282ea855393cfb79f1b54bfd14e34a6949d581.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "2bdddb3c8cc9bca9a389fb283fca309fd91c2622141c08efb87ae42c4029fc43", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "64c57bab88532fa80ddca8444efb9ddf77c22ac533a60b50dd0438d0c0535388", "generation_seconds_batch": 23.535764744039625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8692021369934082, "target_z": 1.6406249808784967, "ce": 6.0146708488464355, "genuineness": 4.268857479095459, "identity": 0.48282721638679504, "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_Concentration/2bdddb3c8cc9bca9a389fb283fca309fd91c2622141c08efb87ae42c4029fc43.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "2cf8ec8d5556abf43f39ff13fa74e65fc73f831f908544cb3dc7c698faa3c497", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "1b2ecd7841846720b20509c74eb0c0a922308e4e36c68718fd3c7e707ac48a36", "generation_seconds_batch": 23.823983412003145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.542707920074463, "target_z": 2.5624998419289065, "ce": 6.022613525390625, "genuineness": 4.394378662109375, "identity": 0.5495504140853882, "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_Concentration/2cf8ec8d5556abf43f39ff13fa74e65fc73f831f908544cb3dc7c698faa3c497.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "2d4f29075a1ecc2dcb0a83a95ba033bce6bb13b25db856698b6ea36bf5e74a1a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "bc4583007b1bd222c293af7c43cf2a07f8eb217f76c9d54390ff13acbee5a429", "generation_seconds_batch": 22.597982077044435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0518476963043213, "target_z": 1.8906248381046056, "ce": 6.125868320465088, "genuineness": 4.18099308013916, "identity": 0.5150552988052368, "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_Concentration/2d4f29075a1ecc2dcb0a83a95ba033bce6bb13b25db856698b6ea36bf5e74a1a.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "2d519d7ee66cba154f20d7fafe2c390211f4bc78145b1d4ffda508ea5fb8c08c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "9ce9c347655a28aaf387695363c7b6c35823bb4b362ce8bc83c39bf00fe157d4", "generation_seconds_batch": 18.202600185992196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0575554370880127, "target_z": 1.8984374254261371, "ce": 5.788304805755615, "genuineness": 4.381826400756836, "identity": 0.7875540852546692, "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_Concentration/2d519d7ee66cba154f20d7fafe2c390211f4bc78145b1d4ffda508ea5fb8c08c.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "2db79171df6658b9f453b323d22296f3e3d4c472e6c80a5ebccdd3ed6d9dc21d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "86efae0c4b8cbe7d3fa9dd87bb5b54cf702fbeec34a584c61b0ed1136f52e9e2", "generation_seconds_batch": 18.29296448500827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.25732421875, "target_z": 2.171875044616841, "ce": 5.927301406860352, "genuineness": 4.362998008728027, "identity": 0.47088944911956787, "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_Concentration/2db79171df6658b9f453b323d22296f3e3d4c472e6c80a5ebccdd3ed6d9dc21d.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "2e1c2b081168bd591e17847a9541f219f189ae6fd3125f016abb36484b59fb7c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "661687118142984da421509208213c26edec664dbe1b73a3550ee6f9abaa02f5", "generation_seconds_batch": 22.25641827308573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4240033626556396, "target_z": 1.031250022945804, "ce": 6.173524379730225, "genuineness": 4.093128204345703, "identity": 0.25822263956069946, "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_Concentration/2e1c2b081168bd591e17847a9541f219f189ae6fd3125f016abb36484b59fb7c.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "2eb22a046eb1cabd588551b5f9152a8bbd8990302240af098661742c43bd00f6", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "89bd879e6b6271038dd97caeeff1e8523289be1575089394a10f3c88b192b714", "generation_seconds_batch": 24.232988427043892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3498035669326782, "target_z": 0.9296875299570218, "ce": 6.308549880981445, "genuineness": 4.394378662109375, "identity": 0.5068814754486084, "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_Concentration/2eb22a046eb1cabd588551b5f9152a8bbd8990302240af098661742c43bd00f6.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "2ece1900b3f464247a831e01a6a5f15314de476b94150714b55962e444d38ed8", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f8a3fabcc7e26449f0850006cc2241ce741af8dd1067584b18c838f8fd62b91d", "generation_seconds_batch": 23.07654504000675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7493410110473633, "target_z": 1.476562605168268, "ce": 6.006728172302246, "genuineness": 4.557555198669434, "identity": 0.7853163480758667, "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_Concentration/2ece1900b3f464247a831e01a6a5f15314de476b94150714b55962e444d38ed8.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "2f023592c14ff6f39e3bd24a8496aa86d61ac8303b6657c1c657eb7e48833cfd", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "1212f66b36736d330361429ec9ec922c861963cfddb01b29e2c784ea03e7a276", "generation_seconds_batch": 23.14104578597471, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.017601728439331, "target_z": 1.843749966856061, "ce": 6.0146708488464355, "genuineness": 4.105680465698242, "identity": 0.5561652183532715, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/2f023592c14ff6f39e3bd24a8496aa86d61ac8303b6657c1c657eb7e48833cfd.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "2f3aeefe1e26f215840dd91e2d2f291b0a178edb656f594696038411365fab40", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "685219776814416af35970a8f46f501e7c1a82ad54141606fa3b0a8087f58b88", "generation_seconds_batch": 22.056478400016204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.777879238128662, "target_z": 1.515624889095281, "ce": 6.062326908111572, "genuineness": 4.20609712600708, "identity": 0.2858887016773224, "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_Concentration/2f3aeefe1e26f215840dd91e2d2f291b0a178edb656f594696038411365fab40.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "2f5cb62e78d1568963a45cbd123630e2bc85293d2ee0319964fe1ffcf4834f6a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "ac29fed544e1a0226a79b88d9d2efb474dc8f3baad1773e9ed3dab555fa13354", "generation_seconds_batch": 20.936839570989832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.640895128250122, "target_z": 1.32812507776078, "ce": 6.252951145172119, "genuineness": 4.381826400756836, "identity": 0.5871902108192444, "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_Concentration/2f5cb62e78d1568963a45cbd123630e2bc85293d2ee0319964fe1ffcf4834f6a.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "2f83dcc48310cd90036679f8dfd033fe05cd7878f07f0a2cf424b8aa22ee1bdb", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "413b6574304c8cef729066914363a127aecce8cd67d67e48d35e2b91b773f424", "generation_seconds_batch": 23.15541494905483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9491095542907715, "target_z": 1.7499998980186493, "ce": 6.006728172302246, "genuineness": 4.507347106933594, "identity": 0.7076154351234436, "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_Concentration/2f83dcc48310cd90036679f8dfd033fe05cd7878f07f0a2cf424b8aa22ee1bdb.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "2f9c34ea80fa92df9ed175b632235f095819a1e6ce0983cf0f3a20dcbe97625b", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "672e381c6432470535b57f97e33e824ee9f27c01eaf0f6780ccf584e9b35810f", "generation_seconds_batch": 16.401693274034187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9319865703582764, "target_z": 1.726562462394377, "ce": 5.935244083404541, "genuineness": 4.519899368286133, "identity": 0.6020206212997437, "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_Concentration/2f9c34ea80fa92df9ed175b632235f095819a1e6ce0983cf0f3a20dcbe97625b.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": "2fa7d3524bb54e73aa46647a0f74738617f80b4720618f1a8b8aef907ce76ce0", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "590cf9d6cd4fbdf49b579714f03939ac3615038350a4bfa34b47dce6f66c72d9", "generation_seconds_batch": 20.772065778030083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5198774337768555, "target_z": 2.531250145323425, "ce": 6.0305562019348145, "genuineness": 4.268857479095459, "identity": 0.48509472608566284, "hypothesis": "Ik schreef het nummer op de enveloop, lees het goed en 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_Concentration/2fa7d3524bb54e73aa46647a0f74738617f80b4720618f1a8b8aef907ce76ce0.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "2fba07648ba9660294cf6b6702f2e31ef05a92624abe6fe0c6f03baa7b7b73f5", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "ac359c2d602f96f7c804d9c2f181d7142575f2311a98865d89beb491776224da", "generation_seconds_batch": 18.220657674013637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1317553520202637, "target_z": 2.0000000815850805, "ce": 5.982900142669678, "genuineness": 4.532451152801514, "identity": 0.8304800987243652, "hypothesis": "Ma porte 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_Concentration/2fba07648ba9660294cf6b6702f2e31ef05a92624abe6fe0c6f03baa7b7b73f5.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": "302c13697d605a44c429c7cde5b43d100cb537d8f8a3406f8d7cc2eeb65d4788", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "da08d4e00983f0d19d1b5cafe7d5ecc09337f946103bcbec6a6eea3cb9a0d10d", "generation_seconds_batch": 22.02929779002443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.36006236076355, "target_z": 2.3124999847027974, "ce": 6.395919322967529, "genuineness": 3.986435890197754, "identity": 0.3035898208618164, "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_Concentration/302c13697d605a44c429c7cde5b43d100cb537d8f8a3406f8d7cc2eeb65d4788.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "30c4c7f800f266c2483e6957a217c20b430b21ea990e58f44d4f57ca8a695e90", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "4526715945b74794dd048618606cadcc99925e0e9dffd61c2d81c99dc31e819c", "generation_seconds_batch": 24.58572772704065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.789294719696045, "target_z": 1.5312500637383442, "ce": 5.927301406860352, "genuineness": 4.65797233581543, "identity": 0.6371614933013916, "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_Concentration/30c4c7f800f266c2483e6957a217c20b430b21ea990e58f44d4f57ca8a695e90.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "310710b8cab7db7ed47c6c5f4410ab26056a9bcceffc4e34432ee092cf733472", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d4d7e7c3a3d50029ae68425a773c2cffb64ca10c1ccaefe5503735c79bda7357", "generation_seconds_batch": 22.12301750201732, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.245908737182617, "target_z": 2.1562498699737778, "ce": 6.070269584655762, "genuineness": 4.507347106933594, "identity": 0.5869469046592712, "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_Concentration/310710b8cab7db7ed47c6c5f4410ab26056a9bcceffc4e34432ee092cf733472.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "315fcee1e91253aec305047567a6cc73b039c06f10e91671e60c10b58e458fcf", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "6f76889d71a1a3848a1fde72949acec2a6c868cc90975c687c5326d43ecbcdda", "generation_seconds_batch": 17.747126223985106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0860939025878906, "target_z": 1.9375000356934728, "ce": 6.046441555023193, "genuineness": 3.961331605911255, "identity": 0.6631190776824951, "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_Concentration/315fcee1e91253aec305047567a6cc73b039c06f10e91671e60c10b58e458fcf.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "31cc7a06e616b5ffb89ec3b2c98261c5a22817d2a0f5eca4e3879b4077683284", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "f4ac0d6873b853ce91fedf4002452c7707f87e8383c84503d7dd6d677e93b272", "generation_seconds_batch": 23.26672536402475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3714778423309326, "target_z": 2.3281251593458605, "ce": 6.078212261199951, "genuineness": 4.331617832183838, "identity": 0.21578189730644226, "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_Concentration/31cc7a06e616b5ffb89ec3b2c98261c5a22817d2a0f5eca4e3879b4077683284.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "328ac0c872ae43fd1eb11652e16c287f9618470e4b5b6d4475709e7773243d6d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "19d701550516690bbcd26e573bc4ede951f5a0a41a787b05aaa8c8c3eef7b0f0", "generation_seconds_batch": 18.408381980028935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4696648120880127, "target_z": 1.0937500688374118, "ce": 6.133810997009277, "genuineness": 4.017816066741943, "identity": 0.3824356198310852, "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_Concentration/328ac0c872ae43fd1eb11652e16c287f9618470e4b5b6d4475709e7773243d6d.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "32b92d7fb4053e0f12a98ac4a215f43bdc59ab3515e5159e6618a4a41b4c83c8", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "4f7deefab1e9734eebf982fcc7629dc250ca722753b5d1a5f8ae80c842d4944f", "generation_seconds_batch": 21.852671992965043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6180644035339355, "target_z": 1.2968750548149761, "ce": 6.078212261199951, "genuineness": 4.287685871124268, "identity": 0.42783403396606445, "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_Concentration/32b92d7fb4053e0f12a98ac4a215f43bdc59ab3515e5159e6618a4a41b4c83c8.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "32c07a3f13ece26ecc72edb2973ce199443c514ee08d9e379e980d838da17f57", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "db9ea23a778cda826b1a5623b386b208280707ab689a41f24ee20fe7723b6ee5", "generation_seconds_batch": 23.29170962702483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0233094692230225, "target_z": 1.8515625541775926, "ce": 6.006728172302246, "genuineness": 4.632867813110352, "identity": 0.851916491985321, "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_Concentration/32c07a3f13ece26ecc72edb2973ce199443c514ee08d9e379e980d838da17f57.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "6d3b83c081157061d8bdb9abb44bf768f88b558105e078f6b33bd1d69d4ba9a3", "generation_seconds_batch": 18.783209803979844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.971940279006958, "target_z": 1.7812499209644532, "ce": 6.229123115539551, "genuineness": 4.331617832183838, "identity": 0.8188650608062744, "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_Concentration/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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "897eaa6a26f7e5ed1dea1893eee2ee3d4999dc6703c63d676bb413cf72f1c309", "generation_seconds_batch": 18.060334723093547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.211662769317627, "target_z": 2.109374998725233, "ce": 6.41180419921875, "genuineness": 4.093128204345703, "identity": 0.43194684386253357, "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_Concentration/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.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": "34aa63a83fa750c895eb70f16f0eba126c43dea8109333760a1d5a98f4145692", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "b4c9f5d9a078d4bcc7ff5485727bc41246a10548084310b990193a2ec80c0126", "generation_seconds_batch": 15.67413882294204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7436332702636719, "target_z": 1.4687500178467363, "ce": 6.1020402908325195, "genuineness": 4.325342178344727, "identity": 0.26884621381759644, "hypothesis": "The keys on on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/34aa63a83fa750c895eb70f16f0eba126c43dea8109333760a1d5a98f4145692.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "35116b56dd7a7d872839195bb4533b6ed5ada2f48e7a54e49a34a563af351e80", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "3e1d9c130ea7fdd938b7e78f856a122ea15a9487e947b8e34128207008ccc07d", "generation_seconds_batch": 23.55825656093657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.595233678817749, "target_z": 1.2656250318691722, "ce": 6.292664527893066, "genuineness": 4.7081804275512695, "identity": 0.8517941236495972, "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_Concentration/35116b56dd7a7d872839195bb4533b6ed5ada2f48e7a54e49a34a563af351e80.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "35197c6359a3550a18fc68df1ed4d88242d43252b0ef27fea84f9444b9fb2964", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5e6faec113972149cf757675853f3ec5c83c03ea417de60bc8066f00c7b3dff4", "generation_seconds_batch": 23.236701613059267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.245908737182617, "target_z": 2.1562498699737778, "ce": 6.1020402908325195, "genuineness": 4.400654315948486, "identity": 0.6704239845275879, "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_Concentration/35197c6359a3550a18fc68df1ed4d88242d43252b0ef27fea84f9444b9fb2964.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "36ca5e6b6317ee487f2945d1f71f352ae954705c655da8d71bf3afcd830f3dcd", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "e9920cbe1ade1e3f4996d3bb7070c9ee2b965b166f72f7f2c3198735adb7d679", "generation_seconds_batch": 23.685162128997035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9947710037231445, "target_z": 1.8124999439102571, "ce": 6.1020402908325195, "genuineness": 4.319066047668457, "identity": 0.8319187164306641, "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_Concentration/36ca5e6b6317ee487f2945d1f71f352ae954705c655da8d71bf3afcd830f3dcd.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "36ff63e87d5f6a5681a2da3617e0b57fb200325526dd387181c9448bcf7eefb9", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "25f0aeae307362743f2668230454b83ac0a02295f7356cf28ff969aebf74832d", "generation_seconds_batch": 23.11876611004118, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5153262615203857, "target_z": 1.1562501147290196, "ce": 5.959072113037109, "genuineness": 4.344170093536377, "identity": 0.13443994522094727, "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_Concentration/36ff63e87d5f6a5681a2da3617e0b57fb200325526dd387181c9448bcf7eefb9.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "372a034959c8c38485805c25e86f83f8c6bd2900ef99eba6a3e6aaef7cbff59f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "9be965a79eeda314fa5d027ca760d291efe028c4383afc78c867f0cded3a74c3", "generation_seconds_batch": 17.654171422007494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8463714122772217, "target_z": 1.6093749579326928, "ce": 6.086154937744141, "genuineness": 4.770940780639648, "identity": 0.6095386147499084, "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_Concentration/372a034959c8c38485805c25e86f83f8c6bd2900ef99eba6a3e6aaef7cbff59f.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": "374067592fed9e6d9c57df48fd6359bbec969cde5283a06ece61534283ece78c", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "38dfa7742f247c2fb33ed200922708ceba857b358c1157fd37eee76cc811b040", "generation_seconds_batch": 18.146255129016936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0404324531555176, "target_z": 1.874999989801865, "ce": 5.673136234283447, "genuineness": 4.6956281661987305, "identity": 0.5905218124389648, "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_Concentration/374067592fed9e6d9c57df48fd6359bbec969cde5283a06ece61534283ece78c.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": "380669c261c8b98c69300a0a30be96f5ae4cae8d5af2a4a81679096b49c3587f", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6c189e8c34cc59780f5d7f0ab746bf2318acd6cda62ea61be79bf767a795dd2d", "generation_seconds_batch": 16.77695035992656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3828930854797363, "target_z": 2.3437500076486013, "ce": 5.879645347595215, "genuineness": 4.337893962860107, "identity": 0.5721094608306885, "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_Concentration/380669c261c8b98c69300a0a30be96f5ae4cae8d5af2a4a81679096b49c3587f.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "3859ac3e5e0e08f93185fb53a8a924b8fc1d770054fa6b37e67bb546d5911013", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "ed0327fe8083e215442d82e21558b329f9b1602fe82e7f695ce9fe084dbf56d5", "generation_seconds_batch": 18.0502514350228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.634030818939209, "target_z": 2.687499933712122, "ce": 5.974957466125488, "genuineness": 4.168440818786621, "identity": 0.6718064546585083, "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_Concentration/3859ac3e5e0e08f93185fb53a8a924b8fc1d770054fa6b37e67bb546d5911013.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "3879ebb0557b1cfcd42468368b1e49c59da092b9af728b6c0ad7592c244af094", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "4ef06ffc0db27d84eca5cb5a05e391739a7d899d2a5272876e427630a825421a", "generation_seconds_batch": 23.377332539996132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6351873874664307, "target_z": 1.3203124904392483, "ce": 6.09409761428833, "genuineness": 4.168440818786621, "identity": 0.3470419645309448, "hypothesis": "The door is still open. I'd put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/3879ebb0557b1cfcd42468368b1e49c59da092b9af728b6c0ad7592c244af094.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "390a6a24d4cb8b2ec24d4df1452d25902771b4e2f651191617e20cdceddb3b3e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7f84ade9a767b37ee5199743869549276c2cf299e3847036dd901e29a4b4bfbb", "generation_seconds_batch": 24.073222820996307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.715094804763794, "target_z": 1.4296874075794008, "ce": 6.0146708488464355, "genuineness": 4.268857479095459, "identity": 0.5086753368377686, "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_Concentration/390a6a24d4cb8b2ec24d4df1452d25902771b4e2f651191617e20cdceddb3b3e.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": "39b2a60841dd82d19115daad0e9e35e206e8b61c66eeaded32364ba5c068acc8", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c87d1994f3375dc81e95689fe4f3d152d9496acfb7d141e5d90d40c753d0bff2", "generation_seconds_batch": 18.415697338059545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4696648120880127, "target_z": 1.0937500688374118, "ce": 6.046441555023193, "genuineness": 4.582659721374512, "identity": 0.7608749270439148, "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_Concentration/39b2a60841dd82d19115daad0e9e35e206e8b61c66eeaded32364ba5c068acc8.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "39c6e6e46d660c9daa4b3844f9671903f1f9f5b3cfdf348abab6015d7b47c858", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a0761cae677e277c025b15ad9535e6912d2499b511ffd7fb6a701fab87b0b0f5", "generation_seconds_batch": 22.299379269010387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4924955368041992, "target_z": 1.1250000917832157, "ce": 6.475345611572266, "genuineness": 4.519899368286133, "identity": 0.4800300598144531, "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_Concentration/39c6e6e46d660c9daa4b3844f9671903f1f9f5b3cfdf348abab6015d7b47c858.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "39dce5c5bd5307003ab916b1b9023c94b003a4da787d4db25eb06990898ee3f4", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a4c8c305d1cdcf820409b6eb0c7c1f162b0163dcc5bfba62026c53225bf3c152", "generation_seconds_batch": 24.09214202896692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1774168014526367, "target_z": 2.0625001274766883, "ce": 6.117925643920898, "genuineness": 3.9676074981689453, "identity": 0.6635857224464417, "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_Concentration/39dce5c5bd5307003ab916b1b9023c94b003a4da787d4db25eb06990898ee3f4.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "3a00b3ba39563655a1f61412f46b6acbbfed37b059f4399a90ca259ef17a1701", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "6b46c8d78bc2431e812617285d40d82d81585bfa0d53ef52399adf9087b41eda", "generation_seconds_batch": 24.152118001016788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0518476963043213, "target_z": 1.8906248381046056, "ce": 6.062326908111572, "genuineness": 4.20609712600708, "identity": 0.6241735219955444, "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_Concentration/3a00b3ba39563655a1f61412f46b6acbbfed37b059f4399a90ca259ef17a1701.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "3a15c20b9b8cac98159f75d7aedaf9f75b85c5217e0bb28df254305608683880", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "ea5a70f395b0619b09656662f99083cc64d1fed1fe096336a8e74712e916eac0", "generation_seconds_batch": 24.309824818978086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9947710037231445, "target_z": 1.8124999439102571, "ce": 6.173524379730225, "genuineness": 4.168440818786621, "identity": 0.6618860363960266, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/3a15c20b9b8cac98159f75d7aedaf9f75b85c5217e0bb28df254305608683880.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "3a1aae9b41dc6e2db011c56521bd52fddc920c1985303109cd736da8b9c18cad", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "f4b3ff4cdb8614a5b3b3f763094b9b79f7ced523b69f3d05c014aa9dbeb1a446", "generation_seconds_batch": 23.222721240948886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4285545349121094, "target_z": 2.406250053540209, "ce": 6.197352409362793, "genuineness": 4.532451152801514, "identity": 0.5954559445381165, "hypothesis": "Ik heb het niet klein doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "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_Concentration/3a1aae9b41dc6e2db011c56521bd52fddc920c1985303109cd736da8b9c18cad.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "3a44f32ccca169cca6cf696a551bc51537d0eab8c46b7cc3176a0cbc13b02e42", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "04de713ccf2fa29f4514bb3c9d36051bb0c478c94b90fcedf471482a6d96cc3f", "generation_seconds_batch": 25.67511607997585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.503910779953003, "target_z": 1.1406249400859565, "ce": 6.372091293334961, "genuineness": 4.457139015197754, "identity": 0.25826388597488403, "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_Concentration/3a44f32ccca169cca6cf696a551bc51537d0eab8c46b7cc3176a0cbc13b02e42.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "3a9e30d0e187cb00f7f8abba5823a882445d02c37cd8de0f26b4fb731f9308d7", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "9420b33ba8b9a6f06d91485bb6cde078a7e01574ec13a937ac20acf2f6a4c0aa", "generation_seconds_batch": 24.104666901985183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.063263177871704, "target_z": 1.906250012747669, "ce": 5.637393951416016, "genuineness": 4.381826400756836, "identity": 0.7101231813430786, "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_Concentration/3a9e30d0e187cb00f7f8abba5823a882445d02c37cd8de0f26b4fb731f9308d7.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "3ab2c1a01c74120c73960f32e2c9da4aebb63624157be736fd5479030cdce547", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "703ccb30785fd223f53ae41e3e3f12242685cdd2cf6043e3f66880b56c0a466c", "generation_seconds_batch": 22.691052442998625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9034481048583984, "target_z": 1.6874998521270415, "ce": 6.046441555023193, "genuineness": 4.632867813110352, "identity": 0.5463759899139404, "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_Concentration/3ab2c1a01c74120c73960f32e2c9da4aebb63624157be736fd5479030cdce547.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "3b5d9ef513e4c8222eae7e4c398edac21758db7511b391e023e0c21c75a9b95f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "dfd899d76165464062c214069412bd9c551dc89698611feb9bbb4b2acee2acec", "generation_seconds_batch": 23.6044969370123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.017601728439331, "target_z": 1.843749966856061, "ce": 6.324435234069824, "genuineness": 4.494794845581055, "identity": 0.6864813566207886, "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_Concentration/3b5d9ef513e4c8222eae7e4c398edac21758db7511b391e023e0c21c75a9b95f.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "3c0c7a15f690483c9c3276835d5caab6bee8a29b39dadf3a642863d9c0ee54f0", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "077f4afaa4147bc1b293a4bc60c020efe45f8e12df41bbb6f4292710237d95de", "generation_seconds_batch": 24.073062017094344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.15458607673645, "target_z": 2.0312501045308844, "ce": 6.141753673553467, "genuineness": 4.281409740447998, "identity": 0.6623014807701111, "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_Concentration/3c0c7a15f690483c9c3276835d5caab6bee8a29b39dadf3a642863d9c0ee54f0.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": "3c574bb2f738ebb8942c363cfba97db1ec51de2b03d37067f7adbb47018f7c47", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d541779a75f50c2dfaefd5bce206a8ce1ba9b78acd7928436b93197082d97b25", "generation_seconds_batch": 24.995299836969934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6637258529663086, "target_z": 1.359375100706584, "ce": 6.157639026641846, "genuineness": 4.7081804275512695, "identity": 0.749600350856781, "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_Concentration/3c574bb2f738ebb8942c363cfba97db1ec51de2b03d37067f7adbb47018f7c47.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "a35c1a5440f5a820c7db29afff3b76009798d5440f645fccae431c6f388d8a86", "generation_seconds_batch": 18.768608300946653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0404324531555176, "target_z": 1.874999989801865, "ce": 6.205295085906982, "genuineness": 4.532451152801514, "identity": 0.6238794326782227, "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_Concentration/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "3caef488d268665a00b9c10656cc7d06ed774cbe81edd6108f4576831af9c558", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "086c7fc0aaaac73d9aad53e0e3679f0faa21e1a2155abc0e4f14b0d490ac8871", "generation_seconds_batch": 23.222721240948886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8692021369934082, "target_z": 1.6406249808784967, "ce": 6.141753673553467, "genuineness": 4.3127899169921875, "identity": 0.4530271291732788, "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_Concentration/3caef488d268665a00b9c10656cc7d06ed774cbe81edd6108f4576831af9c558.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": "3d03cadc8963dc7244b638633e7b610b63da2d9f60642f54893856c8d209c368", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4e01dffd6f9719d0e708884843218558109b4f61bf9886bd5b4f04e58a3476ce", "generation_seconds_batch": 22.344761915970594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3144009113311768, "target_z": 2.2499999388111895, "ce": 5.974957466125488, "genuineness": 4.6956281661987305, "identity": 0.7268961071968079, "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_Concentration/3d03cadc8963dc7244b638633e7b610b63da2d9f60642f54893856c8d209c368.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "3d305e2a40d259596f6f679eb3430f57be58b1f438cb6593824b1d97e3d8c1a2", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ca392ca34ce5292c368ffc0f272f5fb148e46808fc3db3cc0fe22d5b35870cfd", "generation_seconds_batch": 23.98502727691084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8235406875610352, "target_z": 1.5781249349868889, "ce": 6.205295085906982, "genuineness": 4.394378662109375, "identity": 0.540944516658783, "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_Concentration/3d305e2a40d259596f6f679eb3430f57be58b1f438cb6593824b1d97e3d8c1a2.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "3dd7f1434dc23854dfb3b268ceb7a35e38ee6408d29ff861c64c5d4818c98dfa", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "8ea8c812f60bf197378ded7a9fb27f75aa07a70598c88d535467012a86046955", "generation_seconds_batch": 18.34578769793734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7550485134124756, "target_z": 1.4843748661494771, "ce": 5.506340026855469, "genuineness": 4.607763767242432, "identity": 0.6910778880119324, "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_Concentration/3dd7f1434dc23854dfb3b268ceb7a35e38ee6408d29ff861c64c5d4818c98dfa.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "3e4c126ad3b2ce62a3be0f46e1805ca7c4c0639d3bed25c83ac6e3df241004d0", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "ea3476c8c55044eb0989b5df8c46a2a90d39c7040c56114a16c3d99312632916", "generation_seconds_batch": 23.750839538057335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9376943111419678, "target_z": 1.7343750497159085, "ce": 5.681078910827637, "genuineness": 4.494794845581055, "identity": 0.4511813223361969, "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_Concentration/3e4c126ad3b2ce62a3be0f46e1805ca7c4c0639d3bed25c83ac6e3df241004d0.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "3e892750c4445066f57cdec5cc9e7eae22bc48f8dbb110d820a9efad4f68890a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "c86843e9f3ae06965727817ad52d57b872dce3f8cf26c2024176f4bcb5d0f89e", "generation_seconds_batch": 24.073062017094344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2002475261688232, "target_z": 2.0937501504224922, "ce": 6.0146708488464355, "genuineness": 4.243753433227539, "identity": 0.5709505081176758, "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_Concentration/3e892750c4445066f57cdec5cc9e7eae22bc48f8dbb110d820a9efad4f68890a.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "3f038e1d9d472e23bd5760a087b5879b1254e804f60532ddc578a91f9d9ccc46", "bucket": "emo_Concentration", "phase": "wording", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "25b813fcf240754bd927415716cb56f477d097c39b4e2c257d4563eb771f58d0", "generation_seconds_batch": 17.47714376600925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9491095542907715, "target_z": 1.7499998980186493, "ce": 6.268836498260498, "genuineness": 4.6956281661987305, "identity": 0.7390673756599426, "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_Concentration/3f038e1d9d472e23bd5760a087b5879b1254e804f60532ddc578a91f9d9ccc46.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "4038a40573d4838cec0b2108765a559ff21e4c09ee189fa22bcbcf52b6ac1fad", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "ec6d25f003cc57626cc9292869a386ce2dfafe561ebdfef5a6bfba1c5e195126", "generation_seconds_batch": 23.938474473077804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.834956169128418, "target_z": 1.593750109629952, "ce": 5.998785495758057, "genuineness": 4.281409740447998, "identity": 0.7243162393569946, "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_Concentration/4038a40573d4838cec0b2108765a559ff21e4c09ee189fa22bcbcf52b6ac1fad.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": "40a328fddbbe324c7e5b1b57745b61f45561ee2326d2e42702e2210fc63780f8", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "06e58ec6fd3d3dcdc2188b91adc1515cabf183f3823e702303f47747a413f9bd", "generation_seconds_batch": 22.840769880916923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.245908737182617, "target_z": 2.1562498699737778, "ce": 6.1894097328186035, "genuineness": 4.331617832183838, "identity": 0.8049178123474121, "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_Concentration/40a328fddbbe324c7e5b1b57745b61f45561ee2326d2e42702e2210fc63780f8.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "4118c7b955518708ad3f90d7f079604314af57fb1d94a73d3e7490a39d0dccbf", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "6116e6f4024da4bc21f1e4dc67eeef2652bb6969247a265c3fe7bac3cd46a867", "generation_seconds_batch": 23.66766610997729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3440959453582764, "target_z": 0.9218751058056515, "ce": 6.109982967376709, "genuineness": 4.595211505889893, "identity": 0.4361414909362793, "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_Concentration/4118c7b955518708ad3f90d7f079604314af57fb1d94a73d3e7490a39d0dccbf.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": "4128af16513b82e10d459ced54e46087df67931c5bec828ac0ac3ccc9aeaec41", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "44615afc056ab33580d0b317cbe27d56cc1550fc86c730508ab9a17a6d7c7197", "generation_seconds_batch": 15.927424791036174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0118939876556396, "target_z": 1.8359373795345293, "ce": 6.141753673553467, "genuineness": 4.413206577301025, "identity": 0.6218302845954895, "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_Concentration/4128af16513b82e10d459ced54e46087df67931c5bec828ac0ac3ccc9aeaec41.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "41a9066e5525bf76b0e8a9e7fadeb86fd971cede3323f4b912bf6d92c9708ac4", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "de98224049505bcefb8cabac0e11d78553d25c035a7be0bf4583a1ddb6f98cd5", "generation_seconds_batch": 22.613633419037797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.034724712371826, "target_z": 1.8671874024803332, "ce": 6.022613525390625, "genuineness": 4.381826400756836, "identity": 0.8178117275238037, "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_Concentration/41a9066e5525bf76b0e8a9e7fadeb86fd971cede3323f4b912bf6d92c9708ac4.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "41d76932130e0a25077ae5557eff38ba05eb1a7c92c2b74cc2db312306f52c18", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "88d8a66ba4680fd7105f962eaa313a99f4b02b61e1441f142e79ad81de80041f", "generation_seconds_batch": 18.458772829035297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1317553520202637, "target_z": 2.0000000815850805, "ce": 6.09409761428833, "genuineness": 3.9801597595214844, "identity": 0.49000611901283264, "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_Concentration/41d76932130e0a25077ae5557eff38ba05eb1a7c92c2b74cc2db312306f52c18.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "4217cfa948957edd99abb0940cb6f102dfc5254ac8fadb900d378747f7d69e65", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "e0148b4a1cf319d74af96e46589f59a3ee6fe14df53bb867e6376cb3235cb590", "generation_seconds_batch": 22.117912009940483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7550485134124756, "target_z": 1.4843748661494771, "ce": 5.7247633934021, "genuineness": 4.607763767242432, "identity": 0.7974101901054382, "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_Concentration/4217cfa948957edd99abb0940cb6f102dfc5254ac8fadb900d378747f7d69e65.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": "42849b71741f861d5a20a15e0e848f7ad710ef80f3fe04e1b938558a56d23a58", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "676d936e2dc800046c27a01dd6271b44d868bd768afcc5a2ac8edeb65f5233af", "generation_seconds_batch": 16.959682912915014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7550485134124756, "target_z": 1.4843748661494771, "ce": 6.467403411865234, "genuineness": 4.337893962860107, "identity": 0.4738326072692871, "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_Concentration/42849b71741f861d5a20a15e0e848f7ad710ef80f3fe04e1b938558a56d23a58.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "42b528fd991f6ecdfd793fa0c64bc2e456a5c1120115510ae004381403a33ea7", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b39bf8b05b00be7bb129d9dd7fa8fbf699ed4fbb3538f2f806ef57a5b3721ac9", "generation_seconds_batch": 23.321187286055647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0404324531555176, "target_z": 1.874999989801865, "ce": 5.760505676269531, "genuineness": 4.193545341491699, "identity": 0.6278244256973267, "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_Concentration/42b528fd991f6ecdfd793fa0c64bc2e456a5c1120115510ae004381403a33ea7.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "430cb1e78a42a7f10f71e29e06aaf5b71ca66112a98bb2cea7641589efcff9ab", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "03403519fb2a977737694f660e550aa4da8935c0c58f17263f45dbbac4fff458", "generation_seconds_batch": 22.021518954075873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8634943962097168, "target_z": 1.6328123935569652, "ce": 6.229123115539551, "genuineness": 4.369274139404297, "identity": 0.5241326689720154, "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_Concentration/430cb1e78a42a7f10f71e29e06aaf5b71ca66112a98bb2cea7641589efcff9ab.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "304f03e6126910735f007f2ceecee796d421810d157e79e7f969d3bb7f2609fd", "generation_seconds_batch": 18.783209803979844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9491095542907715, "target_z": 1.7499998980186493, "ce": 6.197352409362793, "genuineness": 4.444586753845215, "identity": 0.7263805866241455, "hypothesis": "De weg gaat linksaf na de brug. Loopt 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_Concentration/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "43995b16b9c5e7eae777930986b58b3d3e9804a6461c2fab39cd7fe73bc0db8a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "b97c66cb0631124c6ab7f67cbebc28c0f3fabe6897efc12248f2efb86b80338e", "generation_seconds_batch": 22.764010068029165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4285545349121094, "target_z": 2.406250053540209, "ce": 6.1020402908325195, "genuineness": 4.306513786315918, "identity": 0.5694180727005005, "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_Concentration/43995b16b9c5e7eae777930986b58b3d3e9804a6461c2fab39cd7fe73bc0db8a.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": "439b20f8ea4157619a8217cc60a7870661d2eb58ae06380a7d4962a494613ab4", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ea5eb224e8ea5d5198b0548ec3934b0d4c9f127b06b4474c84edd04ce166a091", "generation_seconds_batch": 18.34130750503391, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0404324531555176, "target_z": 1.874999989801865, "ce": 6.260893821716309, "genuineness": 4.319066047668457, "identity": 0.5815705060958862, "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_Concentration/439b20f8ea4157619a8217cc60a7870661d2eb58ae06380a7d4962a494613ab4.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e1cbf31c06705e3b12391e7d36e0bf2fdfaa2af73ae0b945887c1776e017889b", "generation_seconds_batch": 16.16387514793314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.120339870452881, "target_z": 1.9843749069420173, "ce": 6.117925643920898, "genuineness": 4.545003414154053, "identity": 0.7139437198638916, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "43fb3e8182db66d65c939512de6098e89191454d42690b23781043a0d9ca5889", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "a971739c6cd070aaa23f6255d01288cd40cf5577cee8b070885869a61606bfcb", "generation_seconds_batch": 22.869742520037107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5084619522094727, "target_z": 2.5156249706803617, "ce": 6.221180438995361, "genuineness": 4.419482707977295, "identity": 0.7237701416015625, "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_Concentration/43fb3e8182db66d65c939512de6098e89191454d42690b23781043a0d9ca5889.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "44808bac377e0946ea8a6e83dcacd8a81e9a0946270504426e6272ee1227e05f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "907776b0bdef4a83a9a464f7a60b02e77251c6a7a589cdfc5fa98db67e7d757a", "generation_seconds_batch": 23.437643697019666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.640895128250122, "target_z": 1.32812507776078, "ce": 6.292664527893066, "genuineness": 4.243753433227539, "identity": 0.4362456500530243, "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_Concentration/44808bac377e0946ea8a6e83dcacd8a81e9a0946270504426e6272ee1227e05f.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "4494bf1122f9433ad85f7a5ad3fd0ab45c17daae1630137064f46acaaf2dbbef", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "53f717053ddb2aa3a334e31450ea7c42d8dd642e71a3abcacf1c90ae9cc8c43d", "generation_seconds_batch": 18.133696545963176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9605250358581543, "target_z": 1.7656250726617124, "ce": 6.1894097328186035, "genuineness": 4.632867813110352, "identity": 0.6348247528076172, "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_Concentration/4494bf1122f9433ad85f7a5ad3fd0ab45c17daae1630137064f46acaaf2dbbef.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": "44a8acca8667c9da50ba1eb1f862170a73c449dce0ae29606c55def5b36929b8", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3372b8b6a95fe49a37bbe548812057cc1ff68d0bdec6bcc8cc576ec7a4b78401", "generation_seconds_batch": 24.363060246920213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4742159843444824, "target_z": 2.468750099431817, "ce": 6.173524379730225, "genuineness": 4.457139015197754, "identity": 0.479902982711792, "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_Concentration/44a8acca8667c9da50ba1eb1f862170a73c449dce0ae29606c55def5b36929b8.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "44c2213fe40a2a0248db9eb62cad775bd83125370718aecd07f3692b1895ffd6", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "76e0b2c5c14889c44c9216672b7ba65fa61939941126eb9939f0547ed6f5ada8", "generation_seconds_batch": 21.11465564602986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7265102863311768, "target_z": 1.4453125822224642, "ce": 6.316492557525635, "genuineness": 4.13078498840332, "identity": 0.18492364883422852, "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_Concentration/44c2213fe40a2a0248db9eb62cad775bd83125370718aecd07f3692b1895ffd6.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "44d5699bae579d5bcc5133d489bf760e475b86200e863561950794346fee5fdb", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "09b60f8cefbcafdd69096ee374c1ccc74ade9172e15c2785bd0a62fd08894601", "generation_seconds_batch": 24.426575263030827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5838183164596558, "target_z": 1.2500000203962702, "ce": 5.371314525604248, "genuineness": 4.381826400756836, "identity": 0.5657289028167725, "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_Concentration/44d5699bae579d5bcc5133d489bf760e475b86200e863561950794346fee5fdb.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "451b63ca28ef1ca83533e3b0e1e55df51db6ea93fdb8f57037b5ee9a9f747673", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "2d7e73d269b0613cd4078d7bef3b82f965126d531ed1026fe2af04441c86a229", "generation_seconds_batch": 21.607821582932957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.348647117614746, "target_z": 2.2968751364000566, "ce": 5.95112943649292, "genuineness": 3.8922953605651855, "identity": 0.24730810523033142, "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_Concentration/451b63ca28ef1ca83533e3b0e1e55df51db6ea93fdb8f57037b5ee9a9f747673.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "458d93bc0788e00ee52f5eaa1be799597a7333f7803632e7a6d19a19b36aa1fb", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "0e2ff9d00160402dcba42ac444fc8df1c58ab32a99467e85dd929fcada6471a1", "generation_seconds_batch": 23.236701613059267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2915701866149902, "target_z": 2.2187499158653856, "ce": 6.078212261199951, "genuineness": 4.582659721374512, "identity": 0.5771647691726685, "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_Concentration/458d93bc0788e00ee52f5eaa1be799597a7333f7803632e7a6d19a19b36aa1fb.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "45c656c8edb4f3680bb8bd206ae18d484c587ae41dbb73697c4fb91688c914e8", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "02b86bbc89c8e7883d347ef5c367cd2625eb339feea43ed08251d1e0d1e224b0", "generation_seconds_batch": 21.712894549942575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8007099628448486, "target_z": 1.546874912041085, "ce": 6.23706579208374, "genuineness": 4.545003414154053, "identity": 0.4234778881072998, "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_Concentration/45c656c8edb4f3680bb8bd206ae18d484c587ae41dbb73697c4fb91688c914e8.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "45debb47a085e5af70f592a650bc0e5aa8e505f51c08a71fae285886f7aecd85", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "94408c03c497acd8f7fa2ae1377b0794e6e6ecec84e4b99a7e88d346b6e03139", "generation_seconds_batch": 22.13358556397725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2230780124664307, "target_z": 2.124999847027974, "ce": 5.911416053771973, "genuineness": 4.444586753845215, "identity": 0.5351536273956299, "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_Concentration/45debb47a085e5af70f592a650bc0e5aa8e505f51c08a71fae285886f7aecd85.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "45e231ad2bf030ea8db6d70092f787d49cee461336b3c63615deb254e853b41b", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "660b4c740cb4edca6aacf7fb4436cdbba2d0108d3ba281ab566d8132a1f2a5eb", "generation_seconds_batch": 22.53777876798995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2002475261688232, "target_z": 2.0937501504224922, "ce": 5.959072113037109, "genuineness": 4.356721878051758, "identity": 0.46263161301612854, "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_Concentration/45e231ad2bf030ea8db6d70092f787d49cee461336b3c63615deb254e853b41b.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "45f58084a0e1d99dd45ce1eb1766076747335b52a84f322926c63984dafad60d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d2b68c01cd10fbe6d9ebe45e28414988575dcf572447c87eaf5169e3dc831f72", "generation_seconds_batch": 22.9003998930566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0575554370880127, "target_z": 1.8984374254261371, "ce": 5.967014789581299, "genuineness": 4.507347106933594, "identity": 0.7327005863189697, "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_Concentration/45f58084a0e1d99dd45ce1eb1766076747335b52a84f322926c63984dafad60d.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "93a26ccb19405b8bde028ccaefdd849f6380b5978e81d68e49b348fa5715cbc1", "generation_seconds_batch": 18.888181941001676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6112000942230225, "target_z": 2.6562499107663182, "ce": 6.300607204437256, "genuineness": 4.293961524963379, "identity": 0.7114303112030029, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, ließ sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "4602d9e6ea2786b264a6d81862a76d8d282b6da36dd30c4da131a8dede384c89", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "4a16c12980d85722e29969d2e0a04c3a207e1cd1494322c12dd405ff91d419d6", "generation_seconds_batch": 23.219786209985614, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6865565776824951, "target_z": 1.3906251236523879, "ce": 5.847874641418457, "genuineness": 4.557555198669434, "identity": 0.6616404056549072, "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_Concentration/4602d9e6ea2786b264a6d81862a76d8d282b6da36dd30c4da131a8dede384c89.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "46226ce75c943135569437a88d926361941ff5be020e4dfbc1bd2cd52162757e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "befc064e399d6adda19fe4fe3c1499fd4715cee85ccc827c0a6d56e54324a5f5", "generation_seconds_batch": 23.72659680491779, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8634943962097168, "target_z": 1.6328123935569652, "ce": 5.839932441711426, "genuineness": 4.381826400756836, "identity": 0.7111157178878784, "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_Concentration/46226ce75c943135569437a88d926361941ff5be020e4dfbc1bd2cd52162757e.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": "463147b2e35fbca3b96b0b6561ac4a1e5c34e5c0fcf2b7b51dc1337efc1c3cb5", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "826426ee9fe2895283f9f360d419c332a0b4cd8f6492c2d6ff83afe549149989", "generation_seconds_batch": 18.76547677500639, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.211662769317627, "target_z": 2.109374998725233, "ce": 6.332377910614014, "genuineness": 4.042920112609863, "identity": 0.3117483854293823, "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_Concentration/463147b2e35fbca3b96b0b6561ac4a1e5c34e5c0fcf2b7b51dc1337efc1c3cb5.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "46bf0ed52c32fd9836fba9fb89f8064360a40277ebf8ea96be045dc3a01f1c08", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "201e3bf462c3030e213d05d50941d73650a50ffece61fd564bb2d4e1f2496579", "generation_seconds_batch": 23.388731069047935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.029017210006714, "target_z": 1.8593751414991242, "ce": 5.824047088623047, "genuineness": 4.532451152801514, "identity": 0.7735142111778259, "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_Concentration/46bf0ed52c32fd9836fba9fb89f8064360a40277ebf8ea96be045dc3a01f1c08.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "471083659368a3beb42943039c068160f8d83bdf2c8040017179900de5a53a4b", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "10276588a4e10e10d12d62b38fe69dfcf3ab9d46f734a970d644dc994ccfdf50", "generation_seconds_batch": 23.422360270982608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6351873874664307, "target_z": 1.3203124904392483, "ce": 5.665193557739258, "genuineness": 4.632867813110352, "identity": 0.47580379247665405, "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_Concentration/471083659368a3beb42943039c068160f8d83bdf2c8040017179900de5a53a4b.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "4752c3dd74c16084fb63efb42efd090f8eb476bd42e2d3b9fdcef89136c73ee6", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "682aa100d5430e9f3b0b80956982bda6a106d7d7cd56e48e33ade087a1162311", "generation_seconds_batch": 17.382057255948894, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8920328617095947, "target_z": 1.6718750038243007, "ce": 5.760505676269531, "genuineness": 4.400654315948486, "identity": 0.5305349826812744, "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_Concentration/4752c3dd74c16084fb63efb42efd090f8eb476bd42e2d3b9fdcef89136c73ee6.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "45042c66e31299c27480bd7b27c94e21b91e554935c732ddd3d0eac905da3cb2", "generation_seconds_batch": 15.179711767937988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2230780124664307, "target_z": 2.124999847027974, "ce": 6.125868320465088, "genuineness": 4.607763767242432, "identity": 0.8186257481575012, "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_Concentration/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "489ef03bffc38d21581d70bc694c5b7cb4d8e78accca104829d7d1d626e736b1", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "fa20dbb71c6cada36c9491506832439b7f8fdffd705524ee2268509b44d259b8", "generation_seconds_batch": 22.030181554029696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5381568670272827, "target_z": 1.1874999745046624, "ce": 5.140976905822754, "genuineness": 4.507347106933594, "identity": 0.7054454684257507, "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_Concentration/489ef03bffc38d21581d70bc694c5b7cb4d8e78accca104829d7d1d626e736b1.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "48d2a93d20207111e6e983ed04f7f0667516b81d2bca17c27c13f6d5f5a40c34", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "691e4b1ade5cba138998827e5ae149bf80b57200084b7ea6506e22114536e5d7", "generation_seconds_batch": 22.40670905902516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9662327766418457, "target_z": 1.773437659983244, "ce": 6.268836498260498, "genuineness": 4.6956281661987305, "identity": 0.4897990822792053, "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_Concentration/48d2a93d20207111e6e983ed04f7f0667516b81d2bca17c27c13f6d5f5a40c34.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "48fca45585edb477d42e3cec2af815bc8390a4db1b34faa555aa98ec5aae75c5", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "b274db667b1bbc758263c7ccbaec5c98143bc8f9bbbb28f334822f36bbba7944", "generation_seconds_batch": 16.401693274034187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.017601728439331, "target_z": 1.843749966856061, "ce": 5.597680568695068, "genuineness": 4.457139015197754, "identity": 0.6578694581985474, "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_Concentration/48fca45585edb477d42e3cec2af815bc8390a4db1b34faa555aa98ec5aae75c5.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "495280cd9af22f6cbe21d43fbf90257349580b139f1c666e27cfde09c8a6ec4e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "97198a29639b1a30e05d264838f317fe4b5eb471fae3cd0fb6608929d6f676c0", "generation_seconds_batch": 23.29170962702483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0575554370880127, "target_z": 1.8984374254261371, "ce": 5.967014789581299, "genuineness": 4.758388519287109, "identity": 0.7281293869018555, "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_Concentration/495280cd9af22f6cbe21d43fbf90257349580b139f1c666e27cfde09c8a6ec4e.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "49b8505488d45c05f13ba878eba3e6f6f54c90f32b8c6790a03970fd4357da85", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "b8b7b3b89d4a77969c5c424195c440fe83b77373e0d395018a362ba709a6e4ef", "generation_seconds_batch": 23.321187286055647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2687394618988037, "target_z": 2.1874998929195817, "ce": 6.0305562019348145, "genuineness": 4.18726921081543, "identity": 0.24539758265018463, "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_Concentration/49b8505488d45c05f13ba878eba3e6f6f54c90f32b8c6790a03970fd4357da85.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "1f676ca6f68ee1f98b4e7cc8bf19993c5940ed77f5f72845924ee74b31dfe77a", "generation_seconds_batch": 17.186505028046668, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8235406875610352, "target_z": 1.5781249349868889, "ce": 6.062326908111572, "genuineness": 3.9048471450805664, "identity": 0.4539778530597687, "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_Concentration/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "49de83433bf8f1c0cb4216012ed5a6b39ec79599e440847b0eb11a6f33f8269f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "d80593f8ded063aed79f3785cae1e32837edaebe7b42ab83cef35c4a0cbfd8a2", "generation_seconds_batch": 22.80388194601983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2801549434661865, "target_z": 2.203125067562645, "ce": 6.109982967376709, "genuineness": 4.20609712600708, "identity": 0.5464510321617126, "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_Concentration/49de83433bf8f1c0cb4216012ed5a6b39ec79599e440847b0eb11a6f33f8269f.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "49f2c2138fe5e66be9f8aa4a9b7570a2960babece51b15ff618d9e62012d5454", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "5da46790fb08433725cab78be09b5dbbd9409a2b6a1d0e22a086d5d13b4a2948", "generation_seconds_batch": 23.07654504000675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9833557605743408, "target_z": 1.7968750956075163, "ce": 5.8875885009765625, "genuineness": 4.231201171875, "identity": 0.8341616988182068, "hypothesis": "La porte est encore ouverte. D'affaire tu es une heure. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.2777777777777778, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/49f2c2138fe5e66be9f8aa4a9b7570a2960babece51b15ff618d9e62012d5454.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": "4a14bc6ff2852d5e8a3093bc33fa9dcab92247da64c96780febb3c677d608608", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "9b01a7558e527b23be216755804ee7f398322111857b63fc64e1bc7dab297e92", "generation_seconds_batch": 17.966092425049283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.15458607673645, "target_z": 2.0312501045308844, "ce": 6.070269584655762, "genuineness": 4.632867813110352, "identity": 0.4307335615158081, "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_Concentration/4a14bc6ff2852d5e8a3093bc33fa9dcab92247da64c96780febb3c677d608608.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "4aa5f079c1e0879059465d87a86e88c752e09053c499be93aa4d98dec82042d2", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "9c548cc512a29ab9b8b203f04b8c8afa77544ab7dc37c83663343893e8c63968", "generation_seconds_batch": 23.538102542050183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8920328617095947, "target_z": 1.6718750038243007, "ce": 5.990842819213867, "genuineness": 4.532451152801514, "identity": 0.5063369274139404, "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_Concentration/4aa5f079c1e0879059465d87a86e88c752e09053c499be93aa4d98dec82042d2.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "4b0489337ad1546a59e0d4acb0d545f8b19fd39bc76b81de7de8f7c968e39028", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "360d6bd1f2064cbc9b3d48d4e135c36400c9ff4a1ac26be737a18a4d6be0ac28", "generation_seconds_batch": 23.377332539996132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9148635864257812, "target_z": 1.7031250267701046, "ce": 6.109982967376709, "genuineness": 3.9299514293670654, "identity": 0.2591853737831116, "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_Concentration/4b0489337ad1546a59e0d4acb0d545f8b19fd39bc76b81de7de8f7c968e39028.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "4b343ee28206f723004f7d98f4866ddaf6164080307550bbd049ea1646dbf314", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "f74f51638d0e78a28f84624df5d310c5c07c7ad291a90f99be98946690df7c17", "generation_seconds_batch": 17.590600222931243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.503910779953003, "target_z": 1.1406249400859565, "ce": 6.165581703186035, "genuineness": 4.394378662109375, "identity": 0.11432431638240814, "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_Concentration/4b343ee28206f723004f7d98f4866ddaf6164080307550bbd049ea1646dbf314.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "4b7b0d138719a7de6b784f843a2fb93feeacc1683627f4a72528b98187ec4e87", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "010074e92640d1418677f2f2954c50544a137249ab28e998451c6de075d0e08a", "generation_seconds_batch": 23.016443202039227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.017601728439331, "target_z": 1.843749966856061, "ce": 6.205295085906982, "genuineness": 4.7332844734191895, "identity": 0.4603329300880432, "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_Concentration/4b7b0d138719a7de6b784f843a2fb93feeacc1683627f4a72528b98187ec4e87.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "4be1168c10208df33edbe865691efc76a3a640e1e2c9156025309b9257e63699", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "e3b8b9ccfa6dfe643be1888680f8daa4849e6da595dd00c23cfbe46648177e69", "generation_seconds_batch": 18.182509802049026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9034481048583984, "target_z": 1.6874998521270415, "ce": 5.9431867599487305, "genuineness": 4.406930446624756, "identity": 0.5959135293960571, "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_Concentration/4be1168c10208df33edbe865691efc76a3a640e1e2c9156025309b9257e63699.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "4bfd04314c1e3ca415610bbad0eeddb8827b87b4a947134e5195172cca03fae3", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "6bd09e462e5a04187d27394a62526e04bec0ba186f796923e9317024fddd0267", "generation_seconds_batch": 23.68769497598987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.063263177871704, "target_z": 1.906250012747669, "ce": 6.23706579208374, "genuineness": 3.8671910762786865, "identity": 0.544715166091919, "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_Concentration/4bfd04314c1e3ca415610bbad0eeddb8827b87b4a947134e5195172cca03fae3.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "4ca9ffd0712309f6c0bc55afe4715ae3d6a9c2c6846ebac1236b7e4f4c10ff53", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "17650a9a9ac3a16e0a91ab90ddad49cc53160e8a76aca48da919557f77b7ba54", "generation_seconds_batch": 24.196402541943826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7208025455474854, "target_z": 1.4374999949009324, "ce": 5.911416053771973, "genuineness": 4.557555198669434, "identity": 0.5870838165283203, "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_Concentration/4ca9ffd0712309f6c0bc55afe4715ae3d6a9c2c6846ebac1236b7e4f4c10ff53.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "4cf9bef32211538177b6edd25d09ecb0ac9d833750d59f0a9e72906925333f8a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "cc07f29e53ed433f17a4e0a14e7c662ad8ab845ae25ccb19049aca457801d179", "generation_seconds_batch": 22.931006058002822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2230780124664307, "target_z": 2.124999847027974, "ce": 6.117925643920898, "genuineness": 4.425758361816406, "identity": 0.6010669469833374, "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_Concentration/4cf9bef32211538177b6edd25d09ecb0ac9d833750d59f0a9e72906925333f8a.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "4d47e2bc266a611d873597f58b7f3578b73008d74f2a8329f1c84acf19a96bea", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "b03a71147ab22584af87ac1689dc724245bb69955d8b03fe74a7b73f2888ea49", "generation_seconds_batch": 23.762027853983454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8920328617095947, "target_z": 1.6718750038243007, "ce": 6.133810997009277, "genuineness": 4.632867813110352, "identity": 0.5947131514549255, "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_Concentration/4d47e2bc266a611d873597f58b7f3578b73008d74f2a8329f1c84acf19a96bea.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "4db3408063234df28d8281a16801f6ac3a98d1e637b6f166229acad604ad08c6", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "a19355dec9d70c345f0831e68756aa922dce0f871b2f5f335b982036bd4623a5", "generation_seconds_batch": 22.36332724103704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.211662769317627, "target_z": 2.109374998725233, "ce": 6.23706579208374, "genuineness": 4.570107460021973, "identity": 0.6805908679962158, "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_Concentration/4db3408063234df28d8281a16801f6ac3a98d1e637b6f166229acad604ad08c6.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "4dfd0b6e44bac8f987ec671dc7311185ad3aeebe8b11b9edca69bf85d7edf2fc", "bucket": "emo_Concentration", "phase": "wording", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "5754d83165a008d31fed0208013439c187d1960eb0608f632b554c7f64fa70fc", "generation_seconds_batch": 16.47890271199867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4468340873718262, "target_z": 1.0625000458916078, "ce": 6.252951145172119, "genuineness": 4.482243061065674, "identity": 0.40984246134757996, "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_Concentration/4dfd0b6e44bac8f987ec671dc7311185ad3aeebe8b11b9edca69bf85d7edf2fc.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "4e4235e29d01bdec56e509c66eaafc2ca7bac8c20e57e3a398b317f38bb5f403", "bucket": "emo_Concentration", "phase": "wording", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "ecd1464cc6c0f42071df2358cb2c84df2c7f0960de105cb461c2c0bf4a8378de", "generation_seconds_batch": 17.524757638922893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0518476963043213, "target_z": 1.8906248381046056, "ce": 6.252951145172119, "genuineness": 4.362998008728027, "identity": 0.6737359166145325, "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_Concentration/4e4235e29d01bdec56e509c66eaafc2ca7bac8c20e57e3a398b317f38bb5f403.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "4ede83bbe193ed5c67aedf05ad55230c8cf9c313bbc60c200286f28bec76e2ce", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "50b6452de0f79e13de1b105a60f8db55353f10c3f79e6cd063641f23f797c7e8", "generation_seconds_batch": 23.455929919029586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5838183164596558, "target_z": 1.2500000203962702, "ce": 6.157639026641846, "genuineness": 4.137060642242432, "identity": 0.7320233583450317, "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_Concentration/4ede83bbe193ed5c67aedf05ad55230c8cf9c313bbc60c200286f28bec76e2ce.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "4f5150efde8154199476f4e67d740cebc1e9973ff22c4706d8182921cf1e2352", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "2d475a1d1ee1fa55a3dc06133f396a231c2ba874e3443ff656b856ffa3bb6a53", "generation_seconds_batch": 24.27551789500285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4011726379394531, "target_z": 1.0, "ce": 5.935244083404541, "genuineness": 4.595211505889893, "identity": 0.4259873330593109, "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_Concentration/4f5150efde8154199476f4e67d740cebc1e9973ff22c4706d8182921cf1e2352.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "502d577edca70d7b4fb83469a92efb288cee0c05e94e83055e6285bacb320b42", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "87c4154830dadb55328e21fefd438934235f4473e09a9d5b281fea2519fa6616", "generation_seconds_batch": 24.08046322898008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.789294719696045, "target_z": 1.5312500637383442, "ce": 6.141753673553467, "genuineness": 4.406930446624756, "identity": 0.7950875163078308, "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_Concentration/502d577edca70d7b4fb83469a92efb288cee0c05e94e83055e6285bacb320b42.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "50433a3b1e22f1d2a65ce347a47af77811c43979fdf9cf2c7f98930faace289b", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "93ea00da5fae6756be3e838ca5207ab69fea18ecd7e61716b0f720612026a0ee", "generation_seconds_batch": 23.14730041497387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7036795616149902, "target_z": 1.4140625592766602, "ce": 5.871703147888184, "genuineness": 4.118232727050781, "identity": 0.3155060112476349, "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_Concentration/50433a3b1e22f1d2a65ce347a47af77811c43979fdf9cf2c7f98930faace289b.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": "5082e2827b94bde4d51f4e7a41914c31b217028ff5e578510e857ac1fd860828", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "a94283621348bdc5871d70667594f4f859288f720e024cc656e598208f11b568", "generation_seconds_batch": 15.364080565050244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1888320446014404, "target_z": 2.078124975779429, "ce": 5.4666266441345215, "genuineness": 4.419482707977295, "identity": 0.6007758378982544, "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_Concentration/5082e2827b94bde4d51f4e7a41914c31b217028ff5e578510e857ac1fd860828.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "5134713d0be37346a499a41fff7ed4c544960aedafb100f976e0a812f207386d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "4879510a1b38dacc2559ff1239d4230c002ed991a0928906872188294a96a4e1", "generation_seconds_batch": 23.94005652796477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9605250358581543, "target_z": 1.7656250726617124, "ce": 6.038498878479004, "genuineness": 4.7332844734191895, "identity": 0.7999786138534546, "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_Concentration/5134713d0be37346a499a41fff7ed4c544960aedafb100f976e0a812f207386d.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "515ef0a31c1e4cdead96143c01cea436209c9e9c132b2b507f3d41fd648703ae", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "bc533d01a07237babd3e51f98c6227fca2f620700dfdeca7d7f1f2743a04945e", "generation_seconds_batch": 25.6741333110258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0860939025878906, "target_z": 1.9375000356934728, "ce": 6.078212261199951, "genuineness": 3.9801597595214844, "identity": 0.7574013471603394, "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_Concentration/515ef0a31c1e4cdead96143c01cea436209c9e9c132b2b507f3d41fd648703ae.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": "51eae0a5ed6595abc92c63d7716c14c3fa9f867c014ca425371b01e116a71d33", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "d5c11e8b4a8dbb417b1ea994b9a769795f414f43c4159701ec23d2fc3e805812", "generation_seconds_batch": 17.963124723057263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.063263177871704, "target_z": 1.906250012747669, "ce": 5.728734970092773, "genuineness": 4.306513786315918, "identity": 0.5412923097610474, "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": 0.120000000000001, "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_Concentration/51eae0a5ed6595abc92c63d7716c14c3fa9f867c014ca425371b01e116a71d33.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "52312fb8a391652f4732158ab8c3078af46370d3d3ee60b46b94dba71943e898", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "94dcbe11924d0ebfe7ca0252236457f55ea0e802b8bf34a50b1e03f6ade1d725", "generation_seconds_batch": 23.77342069603037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.926278829574585, "target_z": 1.7187498750728454, "ce": 5.6413655281066895, "genuineness": 4.218649387359619, "identity": 0.6511313319206238, "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_Concentration/52312fb8a391652f4732158ab8c3078af46370d3d3ee60b46b94dba71943e898.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "527612c2234d3891435550e0e0850b002230ec4b77d398b421fb73456922577b", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "7eb8217f3b7be05efad0d2cc3c269235ddb42c91cf1cb83e523c1142a560e6b0", "generation_seconds_batch": 17.250885035959072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4639570713043213, "target_z": 1.0859374815158802, "ce": 6.125868320465088, "genuineness": 4.306513786315918, "identity": 0.4767371714115143, "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_Concentration/527612c2234d3891435550e0e0850b002230ec4b77d398b421fb73456922577b.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "527fcc87296e67880d2cbf4b73722d2391d4b4e81eb88bd48c1855291316a67e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "723b253dd6446fb60a92ca077a6ba8b4f0bae06f3de5c53b55f5d7f9a5381e02", "generation_seconds_batch": 18.12193335709162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7208025455474854, "target_z": 1.4374999949009324, "ce": 6.165581703186035, "genuineness": 4.457139015197754, "identity": 0.29644978046417236, "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_Concentration/527fcc87296e67880d2cbf4b73722d2391d4b4e81eb88bd48c1855291316a67e.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "52ee84b78f29e7a8751279bb053b4806959e770341174d2c2fc99e188f53a112", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "228f47eb1c0b7268430076fda52f9de1afaded05a7dbd1e3477c74a8b930d801", "generation_seconds_batch": 23.411467954982072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9833557605743408, "target_z": 1.7968750956075163, "ce": 5.792276382446289, "genuineness": 4.400654315948486, "identity": 0.4689580202102661, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinführen.", "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_Concentration/52ee84b78f29e7a8751279bb053b4806959e770341174d2c2fc99e188f53a112.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "53ea48710b1a49231f3abe9b8b4b74950f1f4bf904425b63d099e16edd3be855", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "dd53bd0e5f10fc5d50f29dd359830701b21537b463fa44d0c338b047646e28ad", "generation_seconds_batch": 24.183744042995386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.338388204574585, "target_z": 0.9140625184841198, "ce": 6.372091293334961, "genuineness": 4.570107460021973, "identity": 0.5954328775405884, "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_Concentration/53ea48710b1a49231f3abe9b8b4b74950f1f4bf904425b63d099e16edd3be855.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": "53fa605767026791210b6cf346f37bf7a16630193f99ecccab6d8927258b37a3", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6030ad62429ce044b7c22db1001590ae2336047148928f7febad9e7948b6d97b", "generation_seconds_batch": 20.772065778030083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6911075115203857, "target_z": 2.7656248279064704, "ce": 6.038498878479004, "genuineness": 4.432034492492676, "identity": 0.5902599096298218, "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_Concentration/53fa605767026791210b6cf346f37bf7a16630193f99ecccab6d8927258b37a3.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "54618d866912746238e51b326bf90ed28fb2df0412ebf7d040fde634a09d546d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "baac8df06eea0f5045162ce37fd0290737492efcd792ea726bdd12a222ba6a48", "generation_seconds_batch": 17.82481366500724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.302985668182373, "target_z": 2.2343750905084487, "ce": 6.229123115539551, "genuineness": 4.507347106933594, "identity": 0.7831659913063049, "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_Concentration/54618d866912746238e51b326bf90ed28fb2df0412ebf7d040fde634a09d546d.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "49df39e6d49894eda643ce21fbf6e4e133834705ded18db14553d5f2d5be3982", "generation_seconds_batch": 18.888181941001676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.645446300506592, "target_z": 2.7031251083551853, "ce": 6.197352409362793, "genuineness": 4.068024158477783, "identity": 0.5566576719284058, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, ließ sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "553380c5bb5d717711626492312bc7fe63bf4b8ea84a97960212fec2b1d66f0a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2f8386df1ac4add5d421b54192178cc45f2c8f73694a74a7288747fa50be6039", "generation_seconds_batch": 22.778564439038746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2230780124664307, "target_z": 2.124999847027974, "ce": 6.2767791748046875, "genuineness": 4.582659721374512, "identity": 0.4121266007423401, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen daar samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/553380c5bb5d717711626492312bc7fe63bf4b8ea84a97960212fec2b1d66f0a.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": "55880d678903f38da9a19e62822abaa57399e807db3669f1dad601ebecfe8e76", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "07385867a14f165290011c5ada386b214a96ffc914463a59785f575c2bbcf37d", "generation_seconds_batch": 22.0727027929388, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.36006236076355, "target_z": 2.3124999847027974, "ce": 6.1894097328186035, "genuineness": 4.2249250411987305, "identity": 0.5424388647079468, "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_Concentration/55880d678903f38da9a19e62822abaa57399e807db3669f1dad601ebecfe8e76.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "559f83e5e64c9d2bf184bbf024f890559062a2dae9455bf841fae3ee6a3be7aa", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "3285ace62ed5f748e186de692c2041b10454cd98c7c9660b7bfe56500f7fe413", "generation_seconds_batch": 19.2257806439884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1157888174057007, "target_z": 0.6093750395177734, "ce": 6.324435234069824, "genuineness": 4.362998008728027, "identity": 0.16588163375854492, "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_Concentration/559f83e5e64c9d2bf184bbf024f890559062a2dae9455bf841fae3ee6a3be7aa.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "55b9008843aadaaa02fffbebc88edcb62247858d6526ca406a4e25ea2c96de64", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "3cca7987405b9e1a84c59269f12209397f164f7ff6c95b0df6fa0261ea0bed54", "generation_seconds_batch": 21.934725283063017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.108924627304077, "target_z": 1.9687500586392768, "ce": 5.824047088623047, "genuineness": 4.457139015197754, "identity": 0.6405916213989258, "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_Concentration/55b9008843aadaaa02fffbebc88edcb62247858d6526ca406a4e25ea2c96de64.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "55e45693bf1ab02a0305f126ec3ac4fcca177221e7d6a789c532025cdf9868c9", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "f9b1356f0b27914f291722c79e6804c4be281caf9e74c1aebbb1674558306759", "generation_seconds_batch": 22.78584594395943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8235406875610352, "target_z": 1.5781249349868889, "ce": 5.903473377227783, "genuineness": 4.519899368286133, "identity": 0.7045061588287354, "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_Concentration/55e45693bf1ab02a0305f126ec3ac4fcca177221e7d6a789c532025cdf9868c9.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "55eecf66cbe5834610ce1d4fdc30b4a632878fe77e86a8e01519809fa8fec9a9", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "62eb14c98ba455b0a002f2dbe3a71173062ea74fa0746fbc652905fcd0dc8c5d", "generation_seconds_batch": 17.90320471196901, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8920328617095947, "target_z": 1.6718750038243007, "ce": 5.959072113037109, "genuineness": 4.024092197418213, "identity": 0.3423980474472046, "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_Concentration/55eecf66cbe5834610ce1d4fdc30b4a632878fe77e86a8e01519809fa8fec9a9.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "5610bbd3514884b3ee03dc55e2771a5cb312950b866bcc9f4378075f73e01ed3", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "03c97bca8379f33c1954ee18b7e92d6bc2b93b25d9cc5a6aa0b25f5d71cc9749", "generation_seconds_batch": 16.05528374610003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0404324531555176, "target_z": 1.874999989801865, "ce": 6.086154937744141, "genuineness": 4.595211505889893, "identity": 0.8187676668167114, "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_Concentration/5610bbd3514884b3ee03dc55e2771a5cb312950b866bcc9f4378075f73e01ed3.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "569811b207c6e19752106ff4f6165f6e873acb607c8cc63094502c9eb2aec868", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6da99bf345cfe9141c38bf46d634733db5574d4ad9ec06b16603fc7276a1e63c", "generation_seconds_batch": 23.813022161950357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.166001319885254, "target_z": 2.046874952833625, "ce": 6.1894097328186035, "genuineness": 4.356721878051758, "identity": 0.39991599321365356, "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_Concentration/569811b207c6e19752106ff4f6165f6e873acb607c8cc63094502c9eb2aec868.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "56ce70ab6c7367259d13463908609df5c12e77564391f7450411093ad9dea22f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "9c4c0fb5a9d21fce1064e1bcfc5f94f560de127c9267f165d30c257d2879fea4", "generation_seconds_batch": 23.548990524024703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.15458607673645, "target_z": 2.0312501045308844, "ce": 6.022613525390625, "genuineness": 4.469690799713135, "identity": 0.6588947176933289, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/56ce70ab6c7367259d13463908609df5c12e77564391f7450411093ad9dea22f.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "570d795d82677befaf92d78c0996dba43dd2c48be0bfd95802730ef3de6ccbc9", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "34bfaa39b3a147387e17c7d91b910976c5c9258c02e3694bf911be42a1ae2ad5", "generation_seconds_batch": 23.751405931892805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.954817295074463, "target_z": 1.7578124853401809, "ce": 6.038498878479004, "genuineness": 4.21237325668335, "identity": 0.7547412514686584, "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_Concentration/570d795d82677befaf92d78c0996dba43dd2c48be0bfd95802730ef3de6ccbc9.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "5777a52a89dc0d615581ca70a91c83e54781b6e29a402801c206b2ab9945b36d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "09375d4857d6f82e699646b42b2d45ad80213e244893fee9710ecf2694f9c1a2", "generation_seconds_batch": 23.94005652796477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1431705951690674, "target_z": 2.0156249298878213, "ce": 6.046441555023193, "genuineness": 4.6956281661987305, "identity": 0.563586950302124, "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_Concentration/5777a52a89dc0d615581ca70a91c83e54781b6e29a402801c206b2ab9945b36d.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "577b7b4380fe9814aaffd4c2164af255174101d14950962843197357ceaf8dfb", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "a0838c744665a764783a03fbb721fac0549198e09d8c7a55df6f953818abbc1b", "generation_seconds_batch": 23.87030979001429, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2499191761016846, "target_z": 0.7929687203616699, "ce": 6.348263263702393, "genuineness": 4.432034492492676, "identity": 0.35174113512039185, "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_Concentration/577b7b4380fe9814aaffd4c2164af255174101d14950962843197357ceaf8dfb.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "57d5d562d86559a6fe0882363e57dbb34e0f88199205953c4ca3c182361883c5", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "455003d3fe7a441143b4007cbc9e5de2e62662236ec50dd408cc66dd7295d14e", "generation_seconds_batch": 24.979078728007153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7093873023986816, "target_z": 1.4218751465981918, "ce": 6.316492557525635, "genuineness": 4.394378662109375, "identity": 0.4577676057815552, "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_Concentration/57d5d562d86559a6fe0882363e57dbb34e0f88199205953c4ca3c182361883c5.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": "58241915290f78a6aca80c4e5c000cce41477342e4b49492d58671f0b390d267", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cbba3b20bce2e1b72bcb3d486b8ee049cebe681f3aac42b9d96b9d06e4d728fb", "generation_seconds_batch": 20.989614055026323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0273197889328003, "target_z": 0.48828124139532353, "ce": 6.213237762451172, "genuineness": 4.319066047668457, "identity": 0.6137268543243408, "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_Concentration/58241915290f78a6aca80c4e5c000cce41477342e4b49492d58671f0b390d267.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "583617ceabefd3e6e0d9b3c31b457f6bfd47eca8c4a72f622dc9b9e591ac3dfd", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1229fc995ad013ab485bb44e9de31a80dc1eaeddb611e0f4e9ee920bc887bd7e", "generation_seconds_batch": 17.354506751988083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9662327766418457, "target_z": 1.773437659983244, "ce": 5.855817794799805, "genuineness": 4.507347106933594, "identity": 0.6848243474960327, "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_Concentration/583617ceabefd3e6e0d9b3c31b457f6bfd47eca8c4a72f622dc9b9e591ac3dfd.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "5901f57ea0c3db31286233768cb810f118f3d8b82521fbdb5d3c2a995a5dfb01", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "3cc586c6e330c45338f86c351124dd52caf4911c8c038d4b2db92dd38e4cd356", "generation_seconds_batch": 18.26435303094331, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0061864852905273, "target_z": 1.8281251185533203, "ce": 6.078212261199951, "genuineness": 4.796044826507568, "identity": 0.6057274341583252, "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_Concentration/5901f57ea0c3db31286233768cb810f118f3d8b82521fbdb5d3c2a995a5dfb01.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "59570007e9a28752eeb840c04678e2afcd6d5adf6e985168bf1cf2903e2ea234", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "e5cdef2cae1b073bd910af3aafdd59b03a7e1c39335db59e8aeff327aea44fbe", "generation_seconds_batch": 22.95921578502748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7208025455474854, "target_z": 1.4374999949009324, "ce": 6.268836498260498, "genuineness": 4.143336772918701, "identity": 0.424738347530365, "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_Concentration/59570007e9a28752eeb840c04678e2afcd6d5adf6e985168bf1cf2903e2ea234.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": "5abfa2fac1034710bde7dfa20e934f712e780046c0a35b9c49e6bd2d54bc7795", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "0aac92dda340577c04c4fc10b75203b34019eff5d03df47f2740d47401066398", "generation_seconds_batch": 18.166690652025864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.15458607673645, "target_z": 2.0312501045308844, "ce": 5.824047088623047, "genuineness": 4.268857479095459, "identity": 0.6010759472846985, "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_Concentration/5abfa2fac1034710bde7dfa20e934f712e780046c0a35b9c49e6bd2d54bc7795.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "5b04e98057380684fe6d4a4cde4e017eafa3d53156ffec05f78498471a88572d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "bb2f08a8ee83df7dc84e30c24378c4e4086e9083204c8bd43c5db5a65369063f", "generation_seconds_batch": 24.152118001016788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.091801643371582, "target_z": 1.9453126230150044, "ce": 5.764476776123047, "genuineness": 4.21237325668335, "identity": 0.6213014125823975, "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_Concentration/5b04e98057380684fe6d4a4cde4e017eafa3d53156ffec05f78498471a88572d.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "5b752160e3c0afddefb0600887323ec1551d054699f734241df64c83cebd19a2", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "5634acf53b751e13cf202297ddd5369f7dae77e7d719cac0a63d35e7008f705a", "generation_seconds_batch": 23.852694733068347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.834956169128418, "target_z": 1.593750109629952, "ce": 5.530168056488037, "genuineness": 4.425758361816406, "identity": 0.4655165672302246, "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_Concentration/5b752160e3c0afddefb0600887323ec1551d054699f734241df64c83cebd19a2.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "5b93840e2dc7e76a9d6897492f5848eb169bfcece754a6431053f4a74b540785", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "680aebea6752c3d46d0968c32c03215c24cbfeaf4ba487c34a45db50b9355842", "generation_seconds_batch": 22.288893957040273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.211662769317627, "target_z": 2.109374998725233, "ce": 5.879645347595215, "genuineness": 4.344170093536377, "identity": 0.8427730798721313, "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_Concentration/5b93840e2dc7e76a9d6897492f5848eb169bfcece754a6431053f4a74b540785.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "5be4b7487b27ca0751069de461a1927606a986372ef7cc93ccd6f19294dc559e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "b11a583ea2c3ae686ae697744d40d67a2eecc7100cbb5df29f3251ddeb4d6185", "generation_seconds_batch": 22.267895917990245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1614501476287842, "target_z": 0.6718749222392201, "ce": 6.38003396987915, "genuineness": 4.494794845581055, "identity": 0.4177691638469696, "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_Concentration/5be4b7487b27ca0751069de461a1927606a986372ef7cc93ccd6f19294dc559e.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": "5c2787ca2379d00e34e7c27bf6bcc7cb11b5cd20f48dd9f9737dd15f6915946b", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "1f7c0bceb23015767044df3746013f886fa811a92d08bcf7b844b1359dd6f6fd", "generation_seconds_batch": 17.787177509977482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.063263177871704, "target_z": 1.906250012747669, "ce": 6.324435234069824, "genuineness": 4.243753433227539, "identity": 0.33439019322395325, "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_Concentration/5c2787ca2379d00e34e7c27bf6bcc7cb11b5cd20f48dd9f9737dd15f6915946b.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "5c3a298c39e1c9be878f7e7557bc4cca778954066cf5a0671711fa04fc445553", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "9388c57bc107530acec2965cc0aa9a35f2cf91f6db3c289aaa9fbac6f819653e", "generation_seconds_batch": 24.081029778928496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.715094804763794, "target_z": 1.4296874075794008, "ce": 6.252951145172119, "genuineness": 4.030367851257324, "identity": 0.27519792318344116, "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_Concentration/5c3a298c39e1c9be878f7e7557bc4cca778954066cf5a0671711fa04fc445553.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "5c4d116c9a6699635c7b46e6bed5dfe428b955c7bac7db88cf8ffc06e1d2646b", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "f398a7de78811a2f460fe8b5c6d6902ec849abadff3d152dc49fcb942177bb25", "generation_seconds_batch": 24.130494137993082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.074678421020508, "target_z": 1.9218748610504095, "ce": 6.316492557525635, "genuineness": 4.218649387359619, "identity": 0.664767861366272, "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_Concentration/5c4d116c9a6699635c7b46e6bed5dfe428b955c7bac7db88cf8ffc06e1d2646b.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "5dffa983962707464f7a2ab2d0262cfe3a7f99e12276ef36ff5899e83a7a9d2d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d64def6070c97a962b157ae5f33898ad3df6a24cd3218816222c385c63340505", "generation_seconds_batch": 23.82853389903903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7664639949798584, "target_z": 1.5000000407925402, "ce": 6.0146708488464355, "genuineness": 4.15588903427124, "identity": 0.43158721923828125, "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_Concentration/5dffa983962707464f7a2ab2d0262cfe3a7f99e12276ef36ff5899e83a7a9d2d.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "79f86829429409f1b5e98d0fe5de20614c79cde03c4761cdcbaf7558fc72e470", "generation_seconds_batch": 17.77502266992815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.108924627304077, "target_z": 1.9687500586392768, "ce": 6.109982967376709, "genuineness": 4.111956596374512, "identity": 0.8448218107223511, "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_Concentration/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "5e147c42c1626aff7eb5687839f43d82c41c09cf1522b7f726bcc5575e0e9282", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8b7a44a999ccf4f343c7a7b7d2522a2792ef14ab0d0a0de87746264e6dee71d2", "generation_seconds_batch": 20.77718176296912, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.108924627304077, "target_z": 1.9687500586392768, "ce": 5.77639102935791, "genuineness": 4.432034492492676, "identity": 0.3843618929386139, "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_Concentration/5e147c42c1626aff7eb5687839f43d82c41c09cf1522b7f726bcc5575e0e9282.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "5e4bf8d2cfe25f8ba895cddfd38bc326026d17273e6707bbe8eda9ff294fe789", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0c6f3a7314921cfc35ed50d53e1be57880c133a34aa9f993e1311394b8ef34d4", "generation_seconds_batch": 17.99058594298549, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2870190143585205, "target_z": 0.8437498852709804, "ce": 6.316492557525635, "genuineness": 4.111956596374512, "identity": 0.30211007595062256, "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_Concentration/5e4bf8d2cfe25f8ba895cddfd38bc326026d17273e6707bbe8eda9ff294fe789.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": "5e6a7b82996f8b978bc013dff0d5f5a76da7ab2122cd5f920ba2231804205ce5", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "969375e13a5ca791dd35c9e02b03f0ebdc5c7cf08b43183414907c1b8cbafdec", "generation_seconds_batch": 16.757847122033127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3372316360473633, "target_z": 2.2812499617569935, "ce": 5.879645347595215, "genuineness": 4.519899368286133, "identity": 0.5707988739013672, "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_Concentration/5e6a7b82996f8b978bc013dff0d5f5a76da7ab2122cd5f920ba2231804205ce5.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "5e8238f3fe1cf1d9d293ac7cbaaf6358fac16c808c519bbc625f249cb785844b", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "9cb4d20f353b3aa10c581f307a7aaffb4bad94ac635464a79755312c8614ed0f", "generation_seconds_batch": 18.04743400402367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.39430832862854, "target_z": 2.359374855951342, "ce": 6.109982967376709, "genuineness": 4.1998209953308105, "identity": 0.8182555437088013, "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_Concentration/5e8238f3fe1cf1d9d293ac7cbaaf6358fac16c808c519bbc625f249cb785844b.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "5fcf309ad2ee7b623510018889cc58704f2401f280940b43959a14282f9526e6", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "47d2b701fbda5d85f4d78eba9e6e05516e1a379b2e7478d0d4969e30d35da5bd", "generation_seconds_batch": 23.000692607020028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6180644035339355, "target_z": 1.2968750548149761, "ce": 5.879645347595215, "genuineness": 4.406930446624756, "identity": 0.34959325194358826, "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_Concentration/5fcf309ad2ee7b623510018889cc58704f2401f280940b43959a14282f9526e6.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "5fdc6b5dfa1b7acd00220471a7f7872b9b4f04c45e4eceac71463b6f77836940", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "e6e8ed27f3ab776715ca7dd057af622476f1a0c6c46ce750f6647567bffab614", "generation_seconds_batch": 23.535764744039625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.439969778060913, "target_z": 2.42187490184295, "ce": 5.967014789581299, "genuineness": 4.2249250411987305, "identity": 0.6348984241485596, "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_Concentration/5fdc6b5dfa1b7acd00220471a7f7872b9b4f04c45e4eceac71463b6f77836940.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "5ffc928d7415c9ad61fac61a62b6a3dea2949bcf43066137b89019a89d046e88", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "0fff5026ca0809c75d99f3cc30dfb561bb26e5350110823a5a6e46eb93147ef3", "generation_seconds_batch": 23.265170424012467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.36006236076355, "target_z": 2.3124999847027974, "ce": 6.022613525390625, "genuineness": 4.005263805389404, "identity": 0.47280260920524597, "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_Concentration/5ffc928d7415c9ad61fac61a62b6a3dea2949bcf43066137b89019a89d046e88.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "60d05e69e9e0debd6b01070c0440ae2e0180907429e48a727076463f39c0c58f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "58cbf28853392fbeaafdf9b5ae1ceef9ae910209780091adf0fac071e9d9291c", "generation_seconds_batch": 23.728397047962062, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.485631227493286, "target_z": 2.484374947734558, "ce": 6.09409761428833, "genuineness": 4.406930446624756, "identity": 0.5366406440734863, "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_Concentration/60d05e69e9e0debd6b01070c0440ae2e0180907429e48a727076463f39c0c58f.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "60ddebf244e45e865395adc9988c3b2aff6870819b324b4274cc12f3670a6c64", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3590b8b61d557d298d12ec8f5acacf2615fba3f7a72465bf580dd4a62a880342", "generation_seconds_batch": 23.750839538057335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5267415046691895, "target_z": 1.1718749630317604, "ce": 5.871703147888184, "genuineness": 4.482243061065674, "identity": 0.6554611921310425, "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_Concentration/60ddebf244e45e865395adc9988c3b2aff6870819b324b4274cc12f3670a6c64.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "61422ed2ba61685a896c9cb5f4b5b35c0c9a7e6659f6c2571b7bec7cc890c553", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "b778926df4cc0b47e36d8fc47ad6420bf06596065f27412254999d796dac582a", "generation_seconds_batch": 22.560504838009365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7664639949798584, "target_z": 1.5000000407925402, "ce": 5.669164657592773, "genuineness": 4.519899368286133, "identity": 0.7232464551925659, "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_Concentration/61422ed2ba61685a896c9cb5f4b5b35c0c9a7e6659f6c2571b7bec7cc890c553.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "61a31e3579688dc99d568a1e0bccc83901add1ba6f2edda44494260f09d22e1b", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "396dffd08dbfc31e9c2446fe3ac5fd17e9cc6e68cca19d6a29e42dc0271f2043", "generation_seconds_batch": 22.968119185999967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.926278829574585, "target_z": 1.7187498750728454, "ce": 6.062326908111572, "genuineness": 4.406930446624756, "identity": 0.7383583784103394, "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_Concentration/61a31e3579688dc99d568a1e0bccc83901add1ba6f2edda44494260f09d22e1b.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "61a576426c95a5d7c6904fb6f0379be204edb15b85d979027b56817d5b8f2e4b", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "6d651b9f2bd9783aa49ea8aa59ff386fd3d27954d0fb22637865318593ca3046", "generation_seconds_batch": 24.08483943901956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.017601728439331, "target_z": 1.843749966856061, "ce": 6.054384231567383, "genuineness": 4.400654315948486, "identity": 0.6220158338546753, "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_Concentration/61a576426c95a5d7c6904fb6f0379be204edb15b85d979027b56817d5b8f2e4b.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "61b6eb6c8808f399b943d1ff9ae6ceb405c055c0c8934ac0be0f3687eb0901d7", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "8d2fe8cc017c70a748635e650c4c80b2e234c63da7d4240435bc9e7fbefb006c", "generation_seconds_batch": 23.228264773031697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.166001319885254, "target_z": 2.046874952833625, "ce": 6.149696350097656, "genuineness": 4.268857479095459, "identity": 0.6052712202072144, "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_Concentration/61b6eb6c8808f399b943d1ff9ae6ceb405c055c0c8934ac0be0f3687eb0901d7.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "63240aff00f5d8e917c6179d8927f6bbde453e6386dd20fa20c3b18f8ab19f40", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "2f2527c010da69b595ea8f68fad18fc45aa3f2f57cf9939ee18789ac72e43bb4", "generation_seconds_batch": 23.79532268701587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.302985668182373, "target_z": 2.2343750905084487, "ce": 6.054384231567383, "genuineness": 4.362998008728027, "identity": 0.5478196740150452, "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_Concentration/63240aff00f5d8e917c6179d8927f6bbde453e6386dd20fa20c3b18f8ab19f40.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "6351b3ed185589926e559f6757cacf4a5011ea4fad89e00a767d519c7d90bca2", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "31d6e79730ed0b2499077480c90c93038befa12ccc461345d3a982a48e306693", "generation_seconds_batch": 17.7317154109478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9890632629394531, "target_z": 1.8046873565887254, "ce": 5.831989288330078, "genuineness": 4.68307638168335, "identity": 0.8455097675323486, "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_Concentration/6351b3ed185589926e559f6757cacf4a5011ea4fad89e00a767d519c7d90bca2.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "6378fb59a76c865029210aed8fb7f824811e80660d93343659e012fd3ba9be5e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2443de17a032c70a96a70417bd1cf2c8bfd93bd503e2b06b47511bfb1f49f92d", "generation_seconds_batch": 23.53221224306617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.834956169128418, "target_z": 1.593750109629952, "ce": 6.308549880981445, "genuineness": 4.400654315948486, "identity": 0.5060858726501465, "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_Concentration/6378fb59a76c865029210aed8fb7f824811e80660d93343659e012fd3ba9be5e.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "63888f01f13a240b8dd1f801f34c407c4aa77729a2790214a4afe961f2e373c8", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "df135bf601a412cc68d98ced24b5f83dc87fd3ddc1f55c5654c29e30eb2bab60", "generation_seconds_batch": 24.88962646597065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7493410110473633, "target_z": 1.476562605168268, "ce": 6.1020402908325195, "genuineness": 4.193545341491699, "identity": 0.22104892134666443, "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_Concentration/63888f01f13a240b8dd1f801f34c407c4aa77729a2790214a4afe961f2e373c8.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "63ca1541fc725d9e3de61a333b7164f03e8ca331e0e40f09c47eebc3c7b88e18", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "7d4477c476ae38348f7951c20b27aec33bd270ffd6217c78a486aebf614909b1", "generation_seconds_batch": 17.382057255948894, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9148635864257812, "target_z": 1.7031250267701046, "ce": 5.998785495758057, "genuineness": 4.306513786315918, "identity": 0.6755956411361694, "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_Concentration/63ca1541fc725d9e3de61a333b7164f03e8ca331e0e40f09c47eebc3c7b88e18.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "63f670a1b78b11d80c22bb7c68e0e0ffc3ae915399564153b0595909c4b24825", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "3ea50e0644fb5c1d81b6b79edece641503090392d52895385c79e8585d3ba5ab", "generation_seconds_batch": 25.237184253055602, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.063263177871704, "target_z": 1.906250012747669, "ce": 6.117925643920898, "genuineness": 4.796044826507568, "identity": 0.6370811462402344, "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_Concentration/63f670a1b78b11d80c22bb7c68e0e0ffc3ae915399564153b0595909c4b24825.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "6435680528a24f0d99d75e1de7ffe8cae6449bfea1324be8a4b18ffb3b0116e6", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "237ae08884c2509db2382da8fe12a670d55cbebe2ba44e63a59c98a1ad458870", "generation_seconds_batch": 16.742083896999247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0975091457366943, "target_z": 1.9531248839962134, "ce": 5.998785495758057, "genuineness": 4.042920112609863, "identity": 0.6633690595626831, "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_Concentration/6435680528a24f0d99d75e1de7ffe8cae6449bfea1324be8a4b18ffb3b0116e6.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "646925b001687c8d2691bb510fd52f39a6a51147190598acfc2378fd6bf9b679", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "7fbcbf92350a02c333a168425f00da1dcc37320cf66fb2ccf55da33104b3ceda", "generation_seconds_batch": 18.536726046935655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.39430832862854, "target_z": 2.359374855951342, "ce": 5.673136234283447, "genuineness": 4.21237325668335, "identity": 0.3514004647731781, "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_Concentration/646925b001687c8d2691bb510fd52f39a6a51147190598acfc2378fd6bf9b679.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "6519a14c8fe54da6e5060bb6d1f0d6a871034d223b42d3d6730a8da1a0872690", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "3b8969031fd193cb8b154a8672721168d83df3c9c896d9ae5c41b5b084331f3f", "generation_seconds_batch": 24.064566385000944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1260476112365723, "target_z": 1.992187494263549, "ce": 6.133810997009277, "genuineness": 4.18099308013916, "identity": 0.46483147144317627, "hypothesis": "Ik heb het een klein doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "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_Concentration/6519a14c8fe54da6e5060bb6d1f0d6a871034d223b42d3d6730a8da1a0872690.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "662292ecabf09bcf9785e03871d0b8d2ec137510eea3892a539c7187f4697f11", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "ef9a4ebf0e09a1e4f899815d8dd1d3c00e6f2df27d5847df3a0fa5b4c74e425e", "generation_seconds_batch": 23.82982732995879, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0061864852905273, "target_z": 1.8281251185533203, "ce": 5.808161735534668, "genuineness": 4.432034492492676, "identity": 0.7461870908737183, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We've regarded ensemble what it contiens.", "wer": 0.3157894736842105, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/662292ecabf09bcf9785e03871d0b8d2ec137510eea3892a539c7187f4697f11.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "662aa480b965eaede462f53b48e47626fe1f0a52a7228b9cd554199b5025dc54", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "50181692247de4acff7a4d941fc0305e602d07ca858b4620451d81a96b761eaa", "generation_seconds_batch": 25.095981247955933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.120339870452881, "target_z": 1.9843749069420173, "ce": 5.816103935241699, "genuineness": 4.394378662109375, "identity": 0.7245716452598572, "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_Concentration/662aa480b965eaede462f53b48e47626fe1f0a52a7228b9cd554199b5025dc54.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "6715c3f319111fce9bbdbfc2ca28e42c6b66db85a220bd6578bad50c27c0384e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "9b8752ac1a7dbee653c6279d6abf70f73721a6f8cb023f09367a3b5d0f47c76c", "generation_seconds_batch": 22.31949495396111, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.108924627304077, "target_z": 1.9687500586392768, "ce": 6.125868320465088, "genuineness": 4.074300289154053, "identity": 0.49941933155059814, "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_Concentration/6715c3f319111fce9bbdbfc2ca28e42c6b66db85a220bd6578bad50c27c0384e.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "6758f1df6fb0cf896a8ffa842c59a4f06deaf32ad1021931cbe930b58fc673fc", "bucket": "emo_Concentration", "phase": "wording", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "a67f445a06fd166b18ed4249941aa710098d5d662252b534bef31bfb96c1f9f0", "generation_seconds_batch": 18.068687148042955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4810800552368164, "target_z": 1.1093749171401526, "ce": 6.09409761428833, "genuineness": 4.319066047668457, "identity": 0.610061764717102, "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_Concentration/6758f1df6fb0cf896a8ffa842c59a4f06deaf32ad1021931cbe930b58fc673fc.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "67b7c07f4256e26017838bfe69f5e800a15ccb6eb6bc4a4e72be06df2cc4aec6", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "c2d06c0a941c89a27fedddf8061604e0ba32141b9e860dd5c5b3a0f025044930", "generation_seconds_batch": 24.36559438391123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5381568670272827, "target_z": 1.1874999745046624, "ce": 6.221180438995361, "genuineness": 4.432034492492676, "identity": 0.5858145356178284, "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_Concentration/67b7c07f4256e26017838bfe69f5e800a15ccb6eb6bc4a4e72be06df2cc4aec6.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "67dea8423aa6eda6991db50f06a3cd72f75a47957d0abf24b920b9a6c0e33e2e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ea273ce95d9f7281b55a27e3338c50cd8d3588aa7ad9c7500a5e4318300a51d0", "generation_seconds_batch": 23.648752513923682, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0404324531555176, "target_z": 1.874999989801865, "ce": 6.221180438995361, "genuineness": 4.18099308013916, "identity": 0.7697436809539795, "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_Concentration/67dea8423aa6eda6991db50f06a3cd72f75a47957d0abf24b920b9a6c0e33e2e.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": "67e32e4425e7a35559c37700ce7cace898418a235906319e0b03ed922051f556", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c129da5b19469125ed8b31aa88d85137cc55805666ac2e70a94709680e24fa11", "generation_seconds_batch": 18.044811928994022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.245908737182617, "target_z": 2.1562498699737778, "ce": 6.260893821716309, "genuineness": 4.400654315948486, "identity": 0.6430636644363403, "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_Concentration/67e32e4425e7a35559c37700ce7cace898418a235906319e0b03ed922051f556.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": "685040ef405f072aef4efc50e8b90bbba7944562b6c305c484b4897a2bdd4e5c", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "52addd88c71d1b2e4584b7322562bf67ba1b0fa84daa056a18420028249edb6c", "generation_seconds_batch": 15.142117582028732, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1032168865203857, "target_z": 1.960937471317745, "ce": 6.006728172302246, "genuineness": 4.482243061065674, "identity": 0.7418434619903564, "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_Concentration/685040ef405f072aef4efc50e8b90bbba7944562b6c305c484b4897a2bdd4e5c.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "68644536dcb118db9a3a2ecff6604c3ffb49d748ad0b1ff22b056a2891429892", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bc8d864d44f30ec340b1148303eaa81a3f0eece1698763a94017ce2207a08ebd", "generation_seconds_batch": 23.46915988600813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4628005027770996, "target_z": 2.453124924788754, "ce": 5.879645347595215, "genuineness": 4.507347106933594, "identity": 0.33762484788894653, "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_Concentration/68644536dcb118db9a3a2ecff6604c3ffb49d748ad0b1ff22b056a2891429892.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": "6885e584aaf52e6f5f7756e640ba187138ae62360ba22794339b4340d07454f7", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "4a957550a4cd228c38e7f7305a906192622831e99c2fe0c514a3230ff846afff", "generation_seconds_batch": 18.06512235593982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1774168014526367, "target_z": 2.0625001274766883, "ce": 6.292664527893066, "genuineness": 4.306513786315918, "identity": 0.34784549474716187, "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_Concentration/6885e584aaf52e6f5f7756e640ba187138ae62360ba22794339b4340d07454f7.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "69729250322d4721ea7e9574925021738d038a9b8d4bf5aad263b0428a957cb2", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "4b09f3ba16abb326a8ef7d1756720788bdfd77b853c5b42b54d5454f4c7f38e2", "generation_seconds_batch": 23.66202667192556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0404324531555176, "target_z": 1.874999989801865, "ce": 6.054384231567383, "genuineness": 4.482243061065674, "identity": 0.7960652112960815, "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_Concentration/69729250322d4721ea7e9574925021738d038a9b8d4bf5aad263b0428a957cb2.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "69a079796edce14b0a5e9a18064ad1f8700afea13209d5ce684f9e4ae35104fe", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ebfe1ee1aa125d1b43f17b2bf186b5c08a89332a2247c032b9266cb9dcbd87bd", "generation_seconds_batch": 23.11876611004118, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5438644886016846, "target_z": 1.1953123986560326, "ce": 6.109982967376709, "genuineness": 4.017816066741943, "identity": 0.13290761411190033, "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_Concentration/69a079796edce14b0a5e9a18064ad1f8700afea13209d5ce684f9e4ae35104fe.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "52ef33190aff25e2b4a94e8be05d96a22644a46dd4c4000caea202f012b3e200", "generation_seconds_batch": 16.360429111053236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3714778423309326, "target_z": 2.3281251593458605, "ce": 6.221180438995361, "genuineness": 3.8671910762786865, "identity": 0.44558414816856384, "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_Concentration/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.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": "6a9286c45d2973848bcd8ec121a895281b532a537ddfeaf0ebcf21048d356c3a", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "59dccbca4352756c3c8715d99c1e5e11f03f1d7000f1eda9fc9afa5dd848de33", "generation_seconds_batch": 16.604044014937244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8577868938446045, "target_z": 1.625000132575756, "ce": 5.911416053771973, "genuineness": 4.344170093536377, "identity": 0.510511577129364, "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_Concentration/6a9286c45d2973848bcd8ec121a895281b532a537ddfeaf0ebcf21048d356c3a.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "6ac4f1aba71d70bf85d32d85185e58b7711a9baf4984b3bbf074125392a06610", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "4aca8ae65b9eca739d796ae8fc0cdc3d3b7c7e8e5dfe3fa3257b908c04e727a9", "generation_seconds_batch": 18.027708064066246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1146323680877686, "target_z": 1.9765626459608083, "ce": 6.24500846862793, "genuineness": 4.174716949462891, "identity": 0.6249082088470459, "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_Concentration/6ac4f1aba71d70bf85d32d85185e58b7711a9baf4984b3bbf074125392a06610.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "6b02c22425f8661fd4cd882da358df44faaefd53b2b8b3d9c8a88561ddef5ea4", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "b8bf5f8f4be31fcc0d1eefe4feeb2df3e9fc2592cc5c67439086ff6e44460c2d", "generation_seconds_batch": 23.65708191297017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7664639949798584, "target_z": 1.5000000407925402, "ce": 5.458683967590332, "genuineness": 4.15588903427124, "identity": 0.755120038986206, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás.", "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_Concentration/6b02c22425f8661fd4cd882da358df44faaefd53b2b8b3d9c8a88561ddef5ea4.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "6b39a5c6a7aad2251093f141aa90b55d981b1f20e5ac5b5404ce72916b498a2e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "678d49611bd907b2b67211e3536b9be6347c273bb573aea49524b2cb4f8be83f", "generation_seconds_batch": 22.31949495396111, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8463714122772217, "target_z": 1.6093749579326928, "ce": 5.780362129211426, "genuineness": 4.20609712600708, "identity": 0.7322877049446106, "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_Concentration/6b39a5c6a7aad2251093f141aa90b55d981b1f20e5ac5b5404ce72916b498a2e.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "6b894fdbc4ec2ee8e1d8e8328bcdaae626f1b4a875021baa947bf31f520a68b3", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "de840c69ebdedc0737750e58fc0534e08ae97a63c3251efe7f58262f1c725fdc", "generation_seconds_batch": 23.89990634692367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8235406875610352, "target_z": 1.5781249349868889, "ce": 6.078212261199951, "genuineness": 4.607763767242432, "identity": 0.6134189963340759, "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_Concentration/6b894fdbc4ec2ee8e1d8e8328bcdaae626f1b4a875021baa947bf31f520a68b3.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c17b92b9aa875718c0fef269b94b2290e91f7ff26e39d524733c87cf1458a7b3", "generation_seconds_batch": 16.16387514793314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.046140193939209, "target_z": 1.8828125771233966, "ce": 6.252951145172119, "genuineness": 4.65797233581543, "identity": 0.7156741619110107, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.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": "6bdbc8dcfe4a8d27bb3a79eb70f8da8570bb909e556cb561ebfe6582fcb71993", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "9d6c4c2c7f619ac6f46ba2a6aa18004960534d3a97f7d687b6c9be016fc09e5f", "generation_seconds_batch": 17.241669429000467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1774168014526367, "target_z": 2.0625001274766883, "ce": 6.41180419921875, "genuineness": 4.469690799713135, "identity": 0.19263306260108948, "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_Concentration/6bdbc8dcfe4a8d27bb3a79eb70f8da8570bb909e556cb561ebfe6582fcb71993.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "6c63adcf24a0dd3c129468ca458b380b18a7cb0aa0a3d618e0e1aa8029b07248", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "447ec0c5180083a386933d19f4fed426efec1b24d8c8f05ea2ba502ae3c1e259", "generation_seconds_batch": 23.6044969370123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.029017210006714, "target_z": 1.8593751414991242, "ce": 6.340320587158203, "genuineness": 4.432034492492676, "identity": 0.6109105348587036, "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_Concentration/6c63adcf24a0dd3c129468ca458b380b18a7cb0aa0a3d618e0e1aa8029b07248.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "6cd7e8a0cf5ccd5a5058109b60dc1b08c2da30d1d542b2be306e488ed0315b46", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "00b6926b812a07ffd564f6d541ca5916397aa542b06d8026d5fd2045a5fd5b2f", "generation_seconds_batch": 23.173379588057287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9491095542907715, "target_z": 1.7499998980186493, "ce": 5.764476776123047, "genuineness": 4.507347106933594, "identity": 0.818078339099884, "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_Concentration/6cd7e8a0cf5ccd5a5058109b60dc1b08c2da30d1d542b2be306e488ed0315b46.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": "6cf5e8f4aec599c8e2029ff97acb45d69b5a4a552f36836fdbea94fe8fcc41a9", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4fd9f52840d075c5d84c0f4f5d5da180b49170006fda7adf947c6e1241f3687e", "generation_seconds_batch": 23.264406607020646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9605250358581543, "target_z": 1.7656250726617124, "ce": 6.435632705688477, "genuineness": 4.570107460021973, "identity": 0.5587284564971924, "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_Concentration/6cf5e8f4aec599c8e2029ff97acb45d69b5a4a552f36836fdbea94fe8fcc41a9.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "6d4c121a2bd65599609411f0883cb579b9dc24dd727682d47bd2aad2e2d6f9f8", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "0f8a491f71d2214064a8684e32fd4306c783552ef1ff8cb01354543133440796", "generation_seconds_batch": 22.13549752801191, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1431705951690674, "target_z": 2.0156249298878213, "ce": 6.062326908111572, "genuineness": 4.268857479095459, "identity": 0.5732836723327637, "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_Concentration/6d4c121a2bd65599609411f0883cb579b9dc24dd727682d47bd2aad2e2d6f9f8.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "6d4f55f0b87ca682c9d51b768d8f236a88f1998330f82e123d604a4bed07fd00", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "51684d199fc357863e99226bf324b512e4a778417d47b087211c3278439b92b3", "generation_seconds_batch": 21.60325988009572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4285545349121094, "target_z": 2.406250053540209, "ce": 6.078212261199951, "genuineness": 4.319066047668457, "identity": 0.5491461753845215, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen het 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_Concentration/6d4f55f0b87ca682c9d51b768d8f236a88f1998330f82e123d604a4bed07fd00.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "6d700787356381228d6a8647abef402f017b7004482dd123d3ef6d302c812ced", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "0f202fbb3b8888959b78a99ea3452c4dc66559a71c6adad38d4e09500d02f267", "generation_seconds_batch": 22.504525715019554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.302985668182373, "target_z": 2.2343750905084487, "ce": 6.078212261199951, "genuineness": 4.344170093536377, "identity": 0.4220036268234253, "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_Concentration/6d700787356381228d6a8647abef402f017b7004482dd123d3ef6d302c812ced.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "6d9addaf61abe4d6df5898b1dc713828572fd623bcdd4034ffcecfcd9b4fafb2", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "f84ce34fcde22e096efc72056bf4bfd7ed709a4b80a65fa33efe9ae87476d7a6", "generation_seconds_batch": 23.49517510505393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7664639949798584, "target_z": 1.5000000407925402, "ce": 6.23706579208374, "genuineness": 4.030367851257324, "identity": 0.2615277171134949, "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_Concentration/6d9addaf61abe4d6df5898b1dc713828572fd623bcdd4034ffcecfcd9b4fafb2.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "6ddae7fca796f2ca9af37f7cb8e6afc6a93ba07369b98b51305cb7eb4b246a3f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "c5984309b5a06241bdb9f8936b43b5d4887d057f111eefc1e5beada56bbf9359", "generation_seconds_batch": 18.267224235925823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9205713272094727, "target_z": 1.7109376140916361, "ce": 6.205295085906982, "genuineness": 4.406930446624756, "identity": 0.5033042430877686, "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_Concentration/6ddae7fca796f2ca9af37f7cb8e6afc6a93ba07369b98b51305cb7eb4b246a3f.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "6dfe8d4d10969f944f3f48a9bdedd8490f35fbed1392b6548bd60e41d5f61869", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "d835d90ab3b8a8cdca3fed3b25de54d6d4efd9ff7d7985d8efc0d6e3eb1a5adb", "generation_seconds_batch": 25.464599517988972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6180644035339355, "target_z": 1.2968750548149761, "ce": 5.665193557739258, "genuineness": 4.507347106933594, "identity": 0.63792884349823, "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_Concentration/6dfe8d4d10969f944f3f48a9bdedd8490f35fbed1392b6548bd60e41d5f61869.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "6e1f0d30d9555978d3c2a3c6ac1eb6f82c168b29565ed846d05ad48298573455", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "6866b4aeaad2062a804ed5c3f6a3ad7dd8ea974cea3b60e55ef40a090ee6b337", "generation_seconds_batch": 18.272697194945067, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.732217788696289, "target_z": 1.4531248432036732, "ce": 6.1020402908325195, "genuineness": 4.557555198669434, "identity": 0.6392099261283875, "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_Concentration/6e1f0d30d9555978d3c2a3c6ac1eb6f82c168b29565ed846d05ad48298573455.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "6e2e142af4ce0792b0c33da80572305d4728ec43d771ad342ebb7802655eec2e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "c5231d393138ef2a21dc6d44ed48a5fee1db6fe5d7decc7de7242baf765051f6", "generation_seconds_batch": 23.629965062020347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8920328617095947, "target_z": 1.6718750038243007, "ce": 6.133810997009277, "genuineness": 4.557555198669434, "identity": 0.8024696707725525, "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_Concentration/6e2e142af4ce0792b0c33da80572305d4728ec43d771ad342ebb7802655eec2e.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "6e52510b56971cec0a959c63836827cb9fff8c40d6010a5e07fd949729f7a0de", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "4cd0d29f6ca57e3316a8350fe10166f1ceaff103a9b98a0809d8ba5185039436", "generation_seconds_batch": 17.998247500974685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0975091457366943, "target_z": 1.9531248839962134, "ce": 6.09409761428833, "genuineness": 4.337893962860107, "identity": 0.699482798576355, "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_Concentration/6e52510b56971cec0a959c63836827cb9fff8c40d6010a5e07fd949729f7a0de.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "6f8bd01ec37a42918cf9f3c9516f41bb23a27755e73c78aedaa5693b6e98995a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "07791ef5547bfd50002682f80e9ecbe24cf2513c39f9d390e43e3236c5244a06", "generation_seconds_batch": 17.6092372010462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.017601728439331, "target_z": 1.843749966856061, "ce": 6.022613525390625, "genuineness": 4.293961524963379, "identity": 0.7563723921775818, "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_Concentration/6f8bd01ec37a42918cf9f3c9516f41bb23a27755e73c78aedaa5693b6e98995a.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "6fba410c8f90c394292fd35792463a6ff77b745a78c84c6c3a5c411db7df580f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "24d7c16e5800f7d3c571e6ba1ed06c2269c013e082b6c17d98bd36c2847d8ea9", "generation_seconds_batch": 22.289799010031857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.531292676925659, "target_z": 2.5468749936261657, "ce": 5.847874641418457, "genuineness": 4.406930446624756, "identity": 0.3476364016532898, "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_Concentration/6fba410c8f90c394292fd35792463a6ff77b745a78c84c6c3a5c411db7df580f.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "700f4d211b4b17962f963b2e07e0cb71fd304208fa9ea3ec85b0255b90db26b9", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "fcab79c9f0d54cbf94ea0e282e0a6f6eea99dd1369442a54e0e9d5245adb0a59", "generation_seconds_batch": 22.732097795931622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7950024604797363, "target_z": 1.539062651059876, "ce": 5.903473377227783, "genuineness": 4.13078498840332, "identity": 0.6010642051696777, "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_Concentration/700f4d211b4b17962f963b2e07e0cb71fd304208fa9ea3ec85b0255b90db26b9.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "707d13e10400af4aeae5e1a254f9446dd89888a89561a180feb06624ced58394", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "56471a937884fe4211c25c1d879dc3bb48cf32ad813ad51896f51ccab44042ce", "generation_seconds_batch": 23.76125874405261, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.063263177871704, "target_z": 1.906250012747669, "ce": 6.133810997009277, "genuineness": 4.325342178344727, "identity": 0.7247018218040466, "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_Concentration/707d13e10400af4aeae5e1a254f9446dd89888a89561a180feb06624ced58394.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "707dea66f7415bd48591c6853f3bb53b5fb188bbec2036f546dc0864244eca4f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a7f2e6292849f6af14918ef000b79a8606ec1bc301ad282edcf6eb1ab2015727", "generation_seconds_batch": 23.7798164220294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6523103713989258, "target_z": 1.3437499260635206, "ce": 6.197352409362793, "genuineness": 4.105680465698242, "identity": 0.2692650556564331, "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_Concentration/707dea66f7415bd48591c6853f3bb53b5fb188bbec2036f546dc0864244eca4f.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "70b6bf594c1ac16a34fef411049588aba66c9f874c73ee0506eaf03c5b0b16f1", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "798cff1b50d05d5aee9309ba8c601adfdd64d8985cb3a4099e19930355167da9", "generation_seconds_batch": 22.30927831400186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6979718208312988, "target_z": 1.4062499719551285, "ce": 5.903473377227783, "genuineness": 4.507347106933594, "identity": 0.4721032977104187, "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_Concentration/70b6bf594c1ac16a34fef411049588aba66c9f874c73ee0506eaf03c5b0b16f1.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "70ef3004a7fd49c0aff12fa7e38e2954e7b9040aee9152e88d5bab66c6ce4c09", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "ed0578799da238085d42d7df76beff6f1ed52b246c65f08d2043b2b43836bd61", "generation_seconds_batch": 24.944193582050502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5552799701690674, "target_z": 1.210937573299096, "ce": 6.427689552307129, "genuineness": 4.570107460021973, "identity": 0.3709498643875122, "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_Concentration/70ef3004a7fd49c0aff12fa7e38e2954e7b9040aee9152e88d5bab66c6ce4c09.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "71173719bf624b62d8e6b770eb3a8b50594d643c901beee5ea1888658feb3ea1", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "54a6000369c312c7b4221b3acba1cbc4b3d27457da018dc1433d0a92397c0180", "generation_seconds_batch": 23.852694733068347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.777879238128662, "target_z": 1.515624889095281, "ce": 5.131048679351807, "genuineness": 4.68307638168335, "identity": 0.6983470320701599, "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_Concentration/71173719bf624b62d8e6b770eb3a8b50594d643c901beee5ea1888658feb3ea1.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": "713b8ddc36cafbc1b147d9a8b02355565b5df34ea95c692d63a298d29ac95604", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c5edd174858bcf3237cafaeba371f6c7aceffe61ddab47e1030b200cb688606", "generation_seconds_batch": 17.781884949072264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.000478744506836, "target_z": 1.8203125312317887, "ce": 6.213237762451172, "genuineness": 4.482243061065674, "identity": 0.5819808840751648, "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_Concentration/713b8ddc36cafbc1b147d9a8b02355565b5df34ea95c692d63a298d29ac95604.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "719d732fd5945e7f7f70be67e6e47ecf6ae2705e17b620ba2c0763ae3697fcc7", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "64b7ebe7802c4b5feaf7c3c2259bae03925c3552f98e13d9230a243201ccb8ac", "generation_seconds_batch": 23.59407083305996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5609875917434692, "target_z": 1.2187499974504663, "ce": 6.308549880981445, "genuineness": 4.482243061065674, "identity": 0.34324783086776733, "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_Concentration/719d732fd5945e7f7f70be67e6e47ecf6ae2705e17b620ba2c0763ae3697fcc7.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": "71ae89db7d37f2c96cf9151717e6558fa0bf4cee1aead7ed0909891f17c5174c", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "212d6f61215ab6fbeb35f77096238fcb309dcac2e72f2ed54922ffcc87c400d0", "generation_seconds_batch": 22.2888374250615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.302985668182373, "target_z": 2.2343750905084487, "ce": 6.109982967376709, "genuineness": 4.293961524963379, "identity": 0.6340805888175964, "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_Concentration/71ae89db7d37f2c96cf9151717e6558fa0bf4cee1aead7ed0909891f17c5174c.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "7271985f17794d22c830432e9d18fc61f9cab8cf08766b8c33947e7bc490abf5", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "3795168aab12c584d1479335518f72487d93a4d4a8fb352b848231913c443459", "generation_seconds_batch": 23.98502727691084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8235406875610352, "target_z": 1.5781249349868889, "ce": 6.268836498260498, "genuineness": 4.193545341491699, "identity": 0.45411622524261475, "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_Concentration/7271985f17794d22c830432e9d18fc61f9cab8cf08766b8c33947e7bc490abf5.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": "72c369fe834f00a53f624cefd178abc5f6865899fae906b5d4ab75eee6f702d7", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "adb17c87516bd91ad084b153fef60cf671ebf579d97a31c7cd64b253ff5cda97", "generation_seconds_batch": 18.089347754023038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.549572229385376, "target_z": 1.2031249859775643, "ce": 6.0146708488464355, "genuineness": 4.400654315948486, "identity": 0.11336806416511536, "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_Concentration/72c369fe834f00a53f624cefd178abc5f6865899fae906b5d4ab75eee6f702d7.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "73389e84466af45a217a60127eb59a2f54a7450441d0e16270e3693e7a2d4892", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d241562cabeaf84bfcd53601a8d9e345bcd2ee685c917ffb2f8ba0906821c9dd", "generation_seconds_batch": 21.80029243498575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6865565776824951, "target_z": 1.3906251236523879, "ce": 6.23706579208374, "genuineness": 4.595211505889893, "identity": 0.6106873750686646, "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_Concentration/73389e84466af45a217a60127eb59a2f54a7450441d0e16270e3693e7a2d4892.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "74313ac4df054d9ee0c799b65c21bb1bc934ae15766fe33779d996543c03317c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "fb6a14e2e625b6574b1e4a89f3b8bed4d041216e34f2c7a80f0b37443fbdccf5", "generation_seconds_batch": 22.93632545194123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0404324531555176, "target_z": 1.874999989801865, "ce": 6.062326908111572, "genuineness": 4.457139015197754, "identity": 0.7383257150650024, "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_Concentration/74313ac4df054d9ee0c799b65c21bb1bc934ae15766fe33779d996543c03317c.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": "74637413b27d040409f2fcf29929987ef10bc4be3496939854c9dc80e7697236", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8db20db409e0525a5ac8d2d9e86b1f3b481649ae460e7843600f2e521319836c", "generation_seconds_batch": 23.146990363951772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.063263177871704, "target_z": 1.906250012747669, "ce": 6.348263263702393, "genuineness": 4.582659721374512, "identity": 0.6900081634521484, "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_Concentration/74637413b27d040409f2fcf29929987ef10bc4be3496939854c9dc80e7697236.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "7513182c3c58ba56dc21fbe738194f24415791a3844d702c0673a8f6f8712223", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "850080f9a2c83768d01d9694b61edd553e992e2f4e7d3e54aa20034d64202f1f", "generation_seconds_batch": 22.912916891044006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8920328617095947, "target_z": 1.6718750038243007, "ce": 5.919358730316162, "genuineness": 3.9801597595214844, "identity": 0.18628109991550446, "hypothesis": "The door is till open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/7513182c3c58ba56dc21fbe738194f24415791a3844d702c0673a8f6f8712223.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": "75b4aad682ec11295b3417a310efd804d3d2b61b72f1950dcce3ff7ce444bee4", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "886447d2b6b931785e3a1e208ffae7442366c78ee825f18efe302e8a0e452d1b", "generation_seconds_batch": 24.709796688053757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0404324531555176, "target_z": 1.874999989801865, "ce": 6.2767791748046875, "genuineness": 4.406930446624756, "identity": 0.7138728499412537, "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_Concentration/75b4aad682ec11295b3417a310efd804d3d2b61b72f1950dcce3ff7ce444bee4.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "75ec10b9e70adf7335120dbda923e48d1047ce8ef81f469685ba0efb5f744d55", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "d9bf1cebb30bfd7de4814d03390a5c1f643b78e4bfa28697fe44362f49f110e9", "generation_seconds_batch": 23.722426072927192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0061864852905273, "target_z": 1.8281251185533203, "ce": 6.09409761428833, "genuineness": 4.168440818786621, "identity": 0.5343360900878906, "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_Concentration/75ec10b9e70adf7335120dbda923e48d1047ce8ef81f469685ba0efb5f744d55.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "7621505588f4f7fc802c2911358d09777a9e49f231126ecc52014f607904627a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "4f5d4f4eb210ebcafe6c3d1f1cb0b1d9642f19c65a03f8482fcb56fcd9ecbb5b", "generation_seconds_batch": 24.13673999393359, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7379255294799805, "target_z": 1.4609374305252047, "ce": 6.24500846862793, "genuineness": 4.331617832183838, "identity": 0.5570825338363647, "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_Concentration/7621505588f4f7fc802c2911358d09777a9e49f231126ecc52014f607904627a.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "76d9914785eda52121ef59cb8d51092cce71b9801cae9ab9b281f7a12960ff3a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "ee6d1fc3eabb1803cac9011990c2b73e0c52427b620d80a427af7f0e4bd41a6a", "generation_seconds_batch": 24.511546889087185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9605250358581543, "target_z": 1.7656250726617124, "ce": 5.855817794799805, "genuineness": 4.432034492492676, "identity": 0.8092010021209717, "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_Concentration/76d9914785eda52121ef59cb8d51092cce71b9801cae9ab9b281f7a12960ff3a.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": "770dd1c7395521d239cd319a0019a66af75446735acce062b969b2be4ccbe91d", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1c4f0f5fa8c0c1f73314b6db782d523085a83b29cdd75f2447705167dac1af75", "generation_seconds_batch": 18.76547677500639, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.063263177871704, "target_z": 1.906250012747669, "ce": 6.53094482421875, "genuineness": 4.432034492492676, "identity": 0.5945188403129578, "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_Concentration/770dd1c7395521d239cd319a0019a66af75446735acce062b969b2be4ccbe91d.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "c1237476ebd3bae9ca5f6a852fa237808dca1469695f79f8291f93567d18bf4f", "generation_seconds_batch": 15.179711767937988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.108924627304077, "target_z": 1.9687500586392768, "ce": 6.165581703186035, "genuineness": 4.570107460021973, "identity": 0.6830555200576782, "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_Concentration/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.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": "77b4c4aa8de13e2a70826bb853f8feb0f1ca6e3f0ed2a92140b613f1abc57798", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "2421bc595105a4a2a721d5b0be79671a4af523652e6be2a3fb415b29a558751e", "generation_seconds_batch": 17.11697677394841, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5724029541015625, "target_z": 1.2343750089233683, "ce": 5.426913261413574, "genuineness": 4.469690799713135, "identity": 0.5805320739746094, "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_Concentration/77b4c4aa8de13e2a70826bb853f8feb0f1ca6e3f0ed2a92140b613f1abc57798.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "77c877470193bf1e4d56db5269ea55aafda9b5750e1b42d72268cf90883e9e03", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "f6544e3b56d08d709c63989afc9acce0f9241835d3128900d7db54882ab14895", "generation_seconds_batch": 23.747077136998996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9605250358581543, "target_z": 1.7656250726617124, "ce": 6.356205940246582, "genuineness": 4.362998008728027, "identity": 0.6808547377586365, "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_Concentration/77c877470193bf1e4d56db5269ea55aafda9b5750e1b42d72268cf90883e9e03.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "78abb93d7216f47086bc921519b3cd689b7d66308b20bbee77908776e78ed6db", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "f4d1cf2ef7baf3edd5093cbb6af079875cfd9fcc644aa87dbc34d4cde3a6cf2b", "generation_seconds_batch": 17.474679620936513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.498203158378601, "target_z": 1.132812515934586, "ce": 6.197352409362793, "genuineness": 4.243753433227539, "identity": 0.24652214348316193, "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_Concentration/78abb93d7216f47086bc921519b3cd689b7d66308b20bbee77908776e78ed6db.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "78bd2540e1bd33eb5737f9528641fc50414cb3b82476f1a4c17ed8221859e630", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "fde3f24523d662e946a364d19fe3d7cb811758661d897c5b5dc95a36fe548dc2", "generation_seconds_batch": 26.163879495928995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4742159843444824, "target_z": 2.468750099431817, "ce": 5.959072113037109, "genuineness": 4.293961524963379, "identity": 0.5375365018844604, "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_Concentration/78bd2540e1bd33eb5737f9528641fc50414cb3b82476f1a4c17ed8221859e630.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "78f32061694512ee56bd06d007e8178d2b2e116d43274280d0702c9967a3c7d4", "bucket": "emo_Concentration", "phase": "wording", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "9710eaf38ff5eba2386b251669ac12cdbcf6bcecf66aaa522af78f6e573a88b7", "generation_seconds_batch": 17.933679629000835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9148635864257812, "target_z": 1.7031250267701046, "ce": 6.078212261199951, "genuineness": 4.218649387359619, "identity": 0.272707998752594, "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_Concentration/78f32061694512ee56bd06d007e8178d2b2e116d43274280d0702c9967a3c7d4.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "1e584029cad2de50def850823fec6938e55ba369a3beb02ea245057054535dd0", "generation_seconds_batch": 18.768608300946653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8692021369934082, "target_z": 1.6406249808784967, "ce": 6.24500846862793, "genuineness": 4.532451152801514, "identity": 0.588239312171936, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "7977744ed19fe1dfe76c453fac8bd2a5ad89a2957fc02e35485ea385e64fc764", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "77f5e930ff2f8648a7028baf1494ee29ff558ac74b1fc639b4f1834f4c9cbc33", "generation_seconds_batch": 17.42223147500772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3258163928985596, "target_z": 2.2656251134542527, "ce": 5.911416053771973, "genuineness": 4.545003414154053, "identity": 0.6047661304473877, "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_Concentration/7977744ed19fe1dfe76c453fac8bd2a5ad89a2957fc02e35485ea385e64fc764.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "79acaf42b155d790efb99eddc070e83850283c104ebf968737396919d62f1a10", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "e6fa2a75e132a4c77f061a767a1f867287807d5bbc3e8ccdf339b2aab1b482f2", "generation_seconds_batch": 23.904881538939662, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.834956169128418, "target_z": 1.593750109629952, "ce": 6.038498878479004, "genuineness": 4.325342178344727, "identity": 0.6180285215377808, "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_Concentration/79acaf42b155d790efb99eddc070e83850283c104ebf968737396919d62f1a10.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "79f25f48f31aa3e4e58557fcffa1b5bdf20ca1b2a5ff34412f9f1f5a99c8279b", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "375ff45f990906c7869c49a29b17b1deb61c2b7fec407ba2119a8316797c7e76", "generation_seconds_batch": 16.268171717994846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2984344959259033, "target_z": 0.8593750599140436, "ce": 5.589737892150879, "genuineness": 4.356721878051758, "identity": 0.5734918117523193, "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_Concentration/79f25f48f31aa3e4e58557fcffa1b5bdf20ca1b2a5ff34412f9f1f5a99c8279b.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "7a1220ae747a48a16ebb73078b97bed51d8624114bc00486d018017dec4b2226", "bucket": "emo_Concentration", "phase": "wording", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "25078d9c8038acac84d24cea188aa9b3bdd0c515cdd0eb29548d46cdc404c2c7", "generation_seconds_batch": 17.518337804009207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0518476963043213, "target_z": 1.8906248381046056, "ce": 6.403861999511719, "genuineness": 4.055472373962402, "identity": 0.44356250762939453, "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_Concentration/7a1220ae747a48a16ebb73078b97bed51d8624114bc00486d018017dec4b2226.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "7a3a213ea2feab0d14d7610c60e10d2fdaeccc784064a3461cf825aa0aea2c3a", "bucket": "emo_Concentration", "phase": "wording", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "c9e7efa4b638e038142c747fcf48cc05daaa202758a6e9f7d40388ae455750cc", "generation_seconds_batch": 17.933679629000835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.640895128250122, "target_z": 1.32812507776078, "ce": 6.1894097328186035, "genuineness": 3.9299514293670654, "identity": 0.29087692499160767, "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_Concentration/7a3a213ea2feab0d14d7610c60e10d2fdaeccc784064a3461cf825aa0aea2c3a.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "7a6b367799a5a4bf63357b78fae3876fe3785af969e885baf2a1a4716f1282f5", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "92f1ca85c3fb5d60e403b8f1abf8a40c3bfc38107c30849bac1539ae6c9b5b5e", "generation_seconds_batch": 23.639730511931702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.852079153060913, "target_z": 1.6171875452542244, "ce": 6.1020402908325195, "genuineness": 4.532451152801514, "identity": 0.5469295978546143, "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_Concentration/7a6b367799a5a4bf63357b78fae3876fe3785af969e885baf2a1a4716f1282f5.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "7a75c4b4653721364a0b1ae6e31d00774920656f2919532b6f07fb270ed60863", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "baf5a1c496adaf09bab0f006699c12261f640e4d46786cbf36c14607bc55fe35", "generation_seconds_batch": 23.904881538939662, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9319865703582764, "target_z": 1.726562462394377, "ce": 5.935244083404541, "genuineness": 4.319066047668457, "identity": 0.7585985660552979, "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_Concentration/7a75c4b4653721364a0b1ae6e31d00774920656f2919532b6f07fb270ed60863.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "7add5a4b50e1a010e72c05e1ce804c765546af3abfacb5dbc7fd9b29dac89b8f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0373ca752a52e6de07c265164a8d697419a815e1a398533c2590fffca92d9a5f", "generation_seconds_batch": 24.481677368981764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9947710037231445, "target_z": 1.8124999439102571, "ce": 5.6254801750183105, "genuineness": 4.582659721374512, "identity": 0.641240119934082, "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_Concentration/7add5a4b50e1a010e72c05e1ce804c765546af3abfacb5dbc7fd9b29dac89b8f.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "7ae7109c0efa19b3e23505fab36ceb100631c3562db33d28fcb30de97113125f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "9e2bfc3c39bb044f65b1c7024476a5cbc2a50bc1149fedc31f6d03b4eef3dc8c", "generation_seconds_batch": 22.732097795931622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2344934940338135, "target_z": 2.140625021671037, "ce": 5.839932441711426, "genuineness": 4.381826400756836, "identity": 0.41180363297462463, "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_Concentration/7ae7109c0efa19b3e23505fab36ceb100631c3562db33d28fcb30de97113125f.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": "7af62f47d4ea85d857c1d94fe9042d33027275b673f73a3eeeec22d76202d89e", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d7d4356d8b0fd1f2d6d08690a2eb4d66342da3d46f61b37f66eb69feedb2965d", "generation_seconds_batch": 18.55700460402295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3144009113311768, "target_z": 2.2499999388111895, "ce": 6.09409761428833, "genuineness": 4.6203155517578125, "identity": 0.7955989837646484, "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_Concentration/7af62f47d4ea85d857c1d94fe9042d33027275b673f73a3eeeec22d76202d89e.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": "7b8f944cb26a2f0c9a691e55bf39abd3560211d82b77fce775df98a52afeb21f", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1efab96caa3ba6f01a5e297a612c5a63d42dd2f318132e3c129554ce19ea7802", "generation_seconds_batch": 24.709796688053757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.166001319885254, "target_z": 2.046874952833625, "ce": 6.221180438995361, "genuineness": 4.306513786315918, "identity": 0.46351009607315063, "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_Concentration/7b8f944cb26a2f0c9a691e55bf39abd3560211d82b77fce775df98a52afeb21f.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "7bbe2775199bec4f727e9716cb578d1845d5dfceea275587c818380352194e5f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0af06b147c70ee090fbb147aa93a77c461d3bf7e6275d4692171813f1e22264a", "generation_seconds_batch": 18.103598022949882, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3155574798583984, "target_z": 0.8828124955383159, "ce": 6.2767791748046875, "genuineness": 4.457139015197754, "identity": 0.40301263332366943, "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_Concentration/7bbe2775199bec4f727e9716cb578d1845d5dfceea275587c818380352194e5f.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "7be1b6a4ce2eda7cb079483709763f50ddd723c7e4e2cbef0f88167e3f335373", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "fd68de280e04755d8466ccbb8d71885b3e9625842595f21a6feb5d9dd0b98d65", "generation_seconds_batch": 24.88962646597065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.566695213317871, "target_z": 1.2265624216018365, "ce": 6.268836498260498, "genuineness": 4.306513786315918, "identity": 0.2044415920972824, "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_Concentration/7be1b6a4ce2eda7cb079483709763f50ddd723c7e4e2cbef0f88167e3f335373.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "7bfd6f4388e5d986aea56052b381f5c821f6f06cd312a308ed02c4f08e7542f8", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "a89d568d34e39cf121ca4c00e0e713bd367c09d191869c796f8fdd5ce85adae6", "generation_seconds_batch": 23.719796108081937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9148635864257812, "target_z": 1.7031250267701046, "ce": 6.125868320465088, "genuineness": 4.469690799713135, "identity": 0.2952443063259125, "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_Concentration/7bfd6f4388e5d986aea56052b381f5c821f6f06cd312a308ed02c4f08e7542f8.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "7c26275a95fba7542a8e9bdec4841e7f1b6107f93b23210f3b7c6b6f9f18a85d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "0ee12159a4ab88b56c3d8c7e2a2836cc20bf3033785c6e5170ce98bb0fa52316", "generation_seconds_batch": 23.869160891044885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6979718208312988, "target_z": 1.4062499719551285, "ce": 6.165581703186035, "genuineness": 4.6956281661987305, "identity": 0.8154125213623047, "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_Concentration/7c26275a95fba7542a8e9bdec4841e7f1b6107f93b23210f3b7c6b6f9f18a85d.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "7c3577706da81a7938d3bcb3da27f83f43a7270d0dfcd5f575ad524537ec7e4d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d2fa8075a6d57b98cf3aaa8ae478319e8c8fff089b19f8b4bd2da1f590c2d607", "generation_seconds_batch": 18.168144646915607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6637258529663086, "target_z": 1.359375100706584, "ce": 6.252951145172119, "genuineness": 4.268857479095459, "identity": 0.42874300479888916, "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_Concentration/7c3577706da81a7938d3bcb3da27f83f43a7270d0dfcd5f575ad524537ec7e4d.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "7c5c0ca8f3d50b796ba6477b4f415ff645c03b5f2685ed3fc7ded2ab6de92fa4", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "d8020b99bee6c87f2c6ca73f54e5e83147f4aa8da16fe17204a85a3f36336fee", "generation_seconds_batch": 22.655093441018835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0233094692230225, "target_z": 1.8515625541775926, "ce": 5.879645347595215, "genuineness": 3.9801597595214844, "identity": 0.43937042355537415, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/7c5c0ca8f3d50b796ba6477b4f415ff645c03b5f2685ed3fc7ded2ab6de92fa4.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "7c6061c36758f65b592105aafed53a6f4099a1b8e751141cd179d5f3e9f86bdb", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "ace1de574f37a82b806e8ce2068d4adf75f41ba853068701303f057afd3c61a3", "generation_seconds_batch": 24.073222820996307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2915701866149902, "target_z": 2.2187499158653856, "ce": 5.871703147888184, "genuineness": 4.331617832183838, "identity": 0.518217921257019, "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_Concentration/7c6061c36758f65b592105aafed53a6f4099a1b8e751141cd179d5f3e9f86bdb.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "7c65e6e5a6d690810ca15d34780daf33c6debc5bff2b8352f2dd8f29c4d6c5d4", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "5943534641a665aa150b3db85e765c485ecc9d0553d05f7b36101a658359c6d2", "generation_seconds_batch": 24.03718310210388, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4742159843444824, "target_z": 2.468750099431817, "ce": 5.998785495758057, "genuineness": 4.2751336097717285, "identity": 0.5464290380477905, "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_Concentration/7c65e6e5a6d690810ca15d34780daf33c6debc5bff2b8352f2dd8f29c4d6c5d4.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "7d66e3824c6b64a26dc00d409a31452df337ce11d68f650d2ca6fc6d1a46a5fe", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "647a23ea831017f265f6b3d8f2b3db6bb3cc614b1a0a137e8c9b3f206fc3753e", "generation_seconds_batch": 17.837136593065225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9662327766418457, "target_z": 1.773437659983244, "ce": 5.609594821929932, "genuineness": 4.444586753845215, "identity": 0.7557031512260437, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/7d66e3824c6b64a26dc00d409a31452df337ce11d68f650d2ca6fc6d1a46a5fe.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "7d93f0b8779cb6a6a1d0296b6138c9276756cfc8b3ec31011abf8e26ff51d6bf", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "88ccad9bdb9c6c88e5c58ca2303299e8d71950e4152ae7988d28830f4ba35d52", "generation_seconds_batch": 17.016493504983373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3258163928985596, "target_z": 2.2656251134542527, "ce": 5.927301406860352, "genuineness": 4.444586753845215, "identity": 0.27533775568008423, "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_Concentration/7d93f0b8779cb6a6a1d0296b6138c9276756cfc8b3ec31011abf8e26ff51d6bf.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "7dba968ba3e6b926bf649836144b4b12bf3d4f2afe4f9ac69b94f09b08ef1dac", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "daadab4bfa427a603db24157d5e4ba7bc65f08e7e52ffe417cb9b8052eb84721", "generation_seconds_batch": 24.050950662000105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.405723810195923, "target_z": 2.3750000305944052, "ce": 5.967014789581299, "genuineness": 4.362998008728027, "identity": 0.5470643043518066, "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_Concentration/7dba968ba3e6b926bf649836144b4b12bf3d4f2afe4f9ac69b94f09b08ef1dac.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": "7e3edc81f05026f54f81d03b380079370b6ef4eca7a44e0cae6a47e2d322c38d", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "67dfaeddfe5e2ba4bae329e94dc2f9e400f7eac5c6e014b68d3eee3580e20e69", "generation_seconds_batch": 16.604044014937244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6637258529663086, "target_z": 1.359375100706584, "ce": 5.4666266441345215, "genuineness": 4.325342178344727, "identity": 0.542568027973175, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik was het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/7e3edc81f05026f54f81d03b380079370b6ef4eca7a44e0cae6a47e2d322c38d.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "7e9b7cb8747f464464e37b70a8bcbbcb15f9874cc2368956001d2e2c14d50228", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "4089aa84bd28648766540ba84e1869a3982bc9a3534d6137a92f642ea68cab71", "generation_seconds_batch": 23.79532268701587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.732217788696289, "target_z": 1.4531248432036732, "ce": 6.09409761428833, "genuineness": 4.193545341491699, "identity": 0.659369945526123, "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_Concentration/7e9b7cb8747f464464e37b70a8bcbbcb15f9874cc2368956001d2e2c14d50228.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": "7ee89ef87e1156135957a34450fceed5be96a355e7e4c4c4705d7e200d82bca3", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "61a412ff4a7a79cc6fa45497a26165876f83bf86c694772fea1a3fab5311b422", "generation_seconds_batch": 17.079252996947616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.39430832862854, "target_z": 2.359374855951342, "ce": 6.09409761428833, "genuineness": 4.250029563903809, "identity": 0.535822868347168, "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_Concentration/7ee89ef87e1156135957a34450fceed5be96a355e7e4c4c4705d7e200d82bca3.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "7f27c0151f153c2cd4faddcff5564f0299a4acb7f9d1cb35fe319cbd003d4c9e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "64aeb00a6fdc7d120c8e1361a64f5419075a42886c0451f2defb600bcef4c495", "generation_seconds_batch": 17.016493504983373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0118939876556396, "target_z": 1.8359373795345293, "ce": 5.935244083404541, "genuineness": 4.281409740447998, "identity": 0.5004679560661316, "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_Concentration/7f27c0151f153c2cd4faddcff5564f0299a4acb7f9d1cb35fe319cbd003d4c9e.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "7f6ee84dca0032832fcb5c6c252c63b69393a186f68dc1536f1b0c936efe5f97", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "714f2415c8d05beb701a3127501fdf9f7fe6ae7995975d267b408f66a86022fe", "generation_seconds_batch": 18.182509802049026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9605250358581543, "target_z": 1.7656250726617124, "ce": 5.998785495758057, "genuineness": 4.7081804275512695, "identity": 0.51673823595047, "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_Concentration/7f6ee84dca0032832fcb5c6c252c63b69393a186f68dc1536f1b0c936efe5f97.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "ea82d5e834241816c6b4af284fae15ffe0a09d65e97964021b7830a5455b453e", "generation_seconds_batch": 17.74098897597287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8463714122772217, "target_z": 1.6093749579326928, "ce": 6.435632705688477, "genuineness": 4.444586753845215, "identity": 0.34020912647247314, "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_Concentration/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "7fcd64fb2fb3a297a371f8c76efdc6262cd734d58461363d50bb82d07adde1d8", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d5e0e4766d6b1c414c3f0f7950a7747a828d66b5a00c90e37e11dd75b9a3979a", "generation_seconds_batch": 24.20745842694305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9376943111419678, "target_z": 1.7343750497159085, "ce": 6.1894097328186035, "genuineness": 4.6956281661987305, "identity": 0.75766521692276, "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_Concentration/7fcd64fb2fb3a297a371f8c76efdc6262cd734d58461363d50bb82d07adde1d8.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "8015b60222f796fcc08b04437bc9cb6fda8ecc062b5b2dba9c8793e328d527ac", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "2b2860cb8fe338a01e5e6a5fd6776443b384254e507bdbcd4a0743690610f7a7", "generation_seconds_batch": 22.06708541198168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.834956169128418, "target_z": 1.593750109629952, "ce": 6.149696350097656, "genuineness": 4.469690799713135, "identity": 0.7353074550628662, "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_Concentration/8015b60222f796fcc08b04437bc9cb6fda8ecc062b5b2dba9c8793e328d527ac.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "801eaca3d15effcfaa63189a6e3c378f0a3af60160155623ad00e200e1da9923", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "8e0c0b94f96df28410c7fead9ffe7d10facf98e5263894abdebbdf4e41f87145", "generation_seconds_batch": 23.580855860025622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.926278829574585, "target_z": 1.7187498750728454, "ce": 5.863759994506836, "genuineness": 4.256305694580078, "identity": 0.6364496946334839, "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_Concentration/801eaca3d15effcfaa63189a6e3c378f0a3af60160155623ad00e200e1da9923.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "803b17ac256f70efc400f30c22627b5d9d86558c1a61caf9e31ea160b30de0e4", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3df90738d28647dcc147dffdd73e3e20b38a35a21fd4263ee91efc7b18d6db25", "generation_seconds_batch": 22.634524176013656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7036795616149902, "target_z": 1.4140625592766602, "ce": 6.292664527893066, "genuineness": 4.3504462242126465, "identity": 0.4560411870479584, "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_Concentration/803b17ac256f70efc400f30c22627b5d9d86558c1a61caf9e31ea160b30de0e4.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "80522a0c16d11ada028aae9c986f35a22b445760c8aeb005cc8e5e9ad72a0a7e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "5ba38927863c2965b171a29fe6c6ef0a6d37ec7dd84f2496abc499d5befc6b32", "generation_seconds_batch": 22.613633419037797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.080386161804199, "target_z": 1.929687448371941, "ce": 6.038498878479004, "genuineness": 4.344170093536377, "identity": 0.8517521023750305, "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_Concentration/80522a0c16d11ada028aae9c986f35a22b445760c8aeb005cc8e5e9ad72a0a7e.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "6ae25dfde275f1326ab03fb1f270899ff17f9dde786d6e1f97a29931776d845c", "generation_seconds_batch": 17.829099813941866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3155574798583984, "target_z": 0.8828124955383159, "ce": 6.324435234069824, "genuineness": 4.507347106933594, "identity": 0.5844330787658691, "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_Concentration/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "80e69a7f7a20f249b81d3ceea7b44ddc73b898a56aa042efcd456e2cd90be912", "bucket": "emo_Concentration", "phase": "wording", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "181fc3496233ddaebb346aab39285ef8d62d565b25d0536f10be9acdf19f6c1c", "generation_seconds_batch": 21.898169263033196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.566695213317871, "target_z": 1.2265624216018365, "ce": 6.324435234069824, "genuineness": 4.607763767242432, "identity": 0.7476155161857605, "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_Concentration/80e69a7f7a20f249b81d3ceea7b44ddc73b898a56aa042efcd456e2cd90be912.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": "80e9f29dd800df00def371f6ded5c910d4620c094f6e762db05ef2649f66a5b9", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "e00079c7655a253d1167589eddd0122f9402a6b1a8f6b241af11dbe1c60e0882", "generation_seconds_batch": 17.787177509977482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9605250358581543, "target_z": 1.7656250726617124, "ce": 6.1894097328186035, "genuineness": 4.243753433227539, "identity": 0.36926913261413574, "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_Concentration/80e9f29dd800df00def371f6ded5c910d4620c094f6e762db05ef2649f66a5b9.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "80fcec8a3d1c1448a527138ef0491ee7e89bde16e2265b0005e9004ae8168494", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c26732bd3dc8e5ab37e82c7cfdaad7023f05e86c1920f660201508b3045d915b", "generation_seconds_batch": 23.899630832951516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.549572229385376, "target_z": 1.2031249859775643, "ce": 6.117925643920898, "genuineness": 4.15588903427124, "identity": 0.3250044286251068, "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_Concentration/80fcec8a3d1c1448a527138ef0491ee7e89bde16e2265b0005e9004ae8168494.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": "815511b48ff0ad66c4e90d41cdbd628daeaa2a05a6c3b5e4ad56a1aca0027349", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9cbf96bc525bef34891cb3ea7fc6043bdcf2a286b6a296d462fcaac4b6646891", "generation_seconds_batch": 17.76742526004091, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9833557605743408, "target_z": 1.7968750956075163, "ce": 6.324435234069824, "genuineness": 4.218649387359619, "identity": 0.2098405659198761, "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_Concentration/815511b48ff0ad66c4e90d41cdbd628daeaa2a05a6c3b5e4ad56a1aca0027349.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "8194bfbdbbee246bdbbdd0cc2a74c12a0c0e568a88c74c7b8ffa34ef69ea5c8a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "a4ebdd06b1cc31e5ef0294463a08a950f7b56caf73ab1604edbb414226a7bcd9", "generation_seconds_batch": 23.639730511931702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.679692268371582, "target_z": 2.74999997960373, "ce": 5.871703147888184, "genuineness": 4.457139015197754, "identity": 0.6058820486068726, "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_Concentration/8194bfbdbbee246bdbbdd0cc2a74c12a0c0e568a88c74c7b8ffa34ef69ea5c8a.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": "81b43d6ae1f543a232d9e0ddea2414e111a8c4cabb4516b259d0a511d0d138c8", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "761d85da626ded730ad09efbdbd336bfc0742f8951b10970feeb1d38b90bacf9", "generation_seconds_batch": 14.740981984999962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9376943111419678, "target_z": 1.7343750497159085, "ce": 5.998785495758057, "genuineness": 3.9676074981689453, "identity": 0.5558617115020752, "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_Concentration/81b43d6ae1f543a232d9e0ddea2414e111a8c4cabb4516b259d0a511d0d138c8.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "81f8231f71b75a08e07004d25c4f179abf6af9d1ececee043bea8bd2f1b1cefa", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "faef7229ba0682680e9dd318406ad723e73caeaeaa48dd911d61de3017a514a8", "generation_seconds_batch": 23.928716331953183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9376943111419678, "target_z": 1.7343750497159085, "ce": 6.006728172302246, "genuineness": 4.243753433227539, "identity": 0.664297342300415, "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_Concentration/81f8231f71b75a08e07004d25c4f179abf6af9d1ececee043bea8bd2f1b1cefa.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "8211ec71b9598bb1e66d627edfd80bef542c2a68bf5c954017c737afb765f3bc", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "a6d406a991334b7abed131ff22016eb89b379e1ebf82b3e8891be3eb24ce6f18", "generation_seconds_batch": 24.58572772704065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1317553520202637, "target_z": 2.0000000815850805, "ce": 5.645336627960205, "genuineness": 4.6705241203308105, "identity": 0.6245472431182861, "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_Concentration/8211ec71b9598bb1e66d627edfd80bef542c2a68bf5c954017c737afb765f3bc.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "82138965e29e48e6e6f15a3dad3ecb50b761b6019241b003f98c29dfdea20e2c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3b94308f0cecdb5498d092636ae2c6b19fd589dbec55d30fcfee5361e9ca9f27", "generation_seconds_batch": 18.408381980028935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.777879238128662, "target_z": 1.515624889095281, "ce": 6.157639026641846, "genuineness": 4.074300289154053, "identity": 0.24716266989707947, "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_Concentration/82138965e29e48e6e6f15a3dad3ecb50b761b6019241b003f98c29dfdea20e2c.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "82e0e00f7e934a9b1d1e4c4cc2b71f228dec095b9150fce6fd3d559a8098545c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f971329a2487ab26c1761bbcd8e343c6f588fa721c4985fa4563ff0df4950ad1", "generation_seconds_batch": 24.13673999393359, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5724029541015625, "target_z": 1.2343750089233683, "ce": 6.070269584655762, "genuineness": 4.469690799713135, "identity": 0.5543614625930786, "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_Concentration/82e0e00f7e934a9b1d1e4c4cc2b71f228dec095b9150fce6fd3d559a8098545c.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "82e257dda9258d1a92d40b5f7366cf59f14d7b71f52f9c9da3310d6c07e19bce", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "8ee8a28f9d4fdab82ccad510028ad8abd3eb92c90c01b4c19629c4790a5b117b", "generation_seconds_batch": 22.657137342030182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.063263177871704, "target_z": 1.906250012747669, "ce": 6.443574905395508, "genuineness": 4.3127899169921875, "identity": 0.572172999382019, "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_Concentration/82e257dda9258d1a92d40b5f7366cf59f14d7b71f52f9c9da3310d6c07e19bce.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "82f909e2060249e1f5ee56d080a9719f947d5e2cb449d8eef35965cadd0dd501", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "43ccc6091d423e6c417d731589f1facb3ae2eb7a0726169f2f6f7f598beb755e", "generation_seconds_batch": 23.60238571697846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2915701866149902, "target_z": 2.2187499158653856, "ce": 5.756534099578857, "genuineness": 4.080576419830322, "identity": 0.4878840446472168, "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_Concentration/82f909e2060249e1f5ee56d080a9719f947d5e2cb449d8eef35965cadd0dd501.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "832524c4f38e7bb48f300847760ecdf2015c5834ce229ba58a665b06e15ecaa7", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "7a0cdef92b246182ca0df95dda6ffeb1ab036156dce3058f4807ec5c37ff025c", "generation_seconds_batch": 22.773432394023985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5438644886016846, "target_z": 1.1953123986560326, "ce": 6.443574905395508, "genuineness": 4.507347106933594, "identity": 0.31887543201446533, "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_Concentration/832524c4f38e7bb48f300847760ecdf2015c5834ce229ba58a665b06e15ecaa7.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "837373f19ed590cdc79d881a0ee9eb4dc4d40fffb888fd54f3b192c4f434a8a0", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "37263e9442ab0c5df43c73de3a40487f00867f371c82d6321cc876664c243083", "generation_seconds_batch": 21.934725283063017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8121254444122314, "target_z": 1.562500086684148, "ce": 5.9431867599487305, "genuineness": 4.68307638168335, "identity": 0.6876141428947449, "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_Concentration/837373f19ed590cdc79d881a0ee9eb4dc4d40fffb888fd54f3b192c4f434a8a0.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "83766b55510ecbe493beb6aab2c79d0dbaea404225fed98e370dc73d0e745038", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "ed7b35ac9d788d1e1efeb67a047ff6c5356b946d3151063c3fddab6907c9d156", "generation_seconds_batch": 23.275602945010178, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8577868938446045, "target_z": 1.625000132575756, "ce": 5.974957466125488, "genuineness": 4.482243061065674, "identity": 0.6023272275924683, "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_Concentration/83766b55510ecbe493beb6aab2c79d0dbaea404225fed98e370dc73d0e745038.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "83905ce0627210f8e6c3ced8c19530ff3107750d6f0ad716d72d418a5c801333", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "0b986bf80166916888102ef102aba053ca6802b7841a39a3ab95bfe3f4dfb8ed", "generation_seconds_batch": 17.087197503075004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6637258529663086, "target_z": 1.359375100706584, "ce": 6.062326908111572, "genuineness": 4.570107460021973, "identity": 0.43145453929901123, "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_Concentration/83905ce0627210f8e6c3ced8c19530ff3107750d6f0ad716d72d418a5c801333.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "844043e5ba648d60a0ddab8744adc99816313bc011d238021ef5ca880161b149", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "9e2cc22e124edea655739a25ebb1540eecfcf490db0e18f1108c41e801252078", "generation_seconds_batch": 23.251021036994644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6751410961151123, "target_z": 1.3749999490093245, "ce": 6.205295085906982, "genuineness": 4.645420074462891, "identity": 0.5458903312683105, "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_Concentration/844043e5ba648d60a0ddab8744adc99816313bc011d238021ef5ca880161b149.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": "84e73459a72be65789db747d464201fd2c418cd1604d9264f1d6453b2a1dad98", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "94ee4db9a0cc0dba95da989278da271ae5e8e54a348c574e0fd540dc1a2efeb2", "generation_seconds_batch": 23.69549362990074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5198774337768555, "target_z": 2.531250145323425, "ce": 6.046441555023193, "genuineness": 4.281409740447998, "identity": 0.5509138107299805, "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_Concentration/84e73459a72be65789db747d464201fd2c418cd1604d9264f1d6453b2a1dad98.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "85394e421d47edb95b9e61bbbf9a4883abc739d0b24900ef02cf9b00c2459dfb", "bucket": "emo_Concentration", "phase": "wording", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "890699859f9c789b13baccc96a46e21f01217f74654ef61bfb6113b4d6aa3e90", "generation_seconds_batch": 17.838366665062495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8692021369934082, "target_z": 1.6406249808784967, "ce": 6.141753673553467, "genuineness": 4.482243061065674, "identity": 0.6724420189857483, "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_Concentration/85394e421d47edb95b9e61bbbf9a4883abc739d0b24900ef02cf9b00c2459dfb.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "8560b11751d298b7d47a6b863c3f92a85f6aefaff3a9b8a25f1222e20161ea1b", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "f55fb8c10f082516b17a4f4f80bba4b7cb367310654b3c3afc6ce0afb451fa8d", "generation_seconds_batch": 22.53777876798995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1032168865203857, "target_z": 1.960937471317745, "ce": 6.038498878479004, "genuineness": 4.381826400756836, "identity": 0.3743748068809509, "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_Concentration/8560b11751d298b7d47a6b863c3f92a85f6aefaff3a9b8a25f1222e20161ea1b.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "858bfba40c0aab783a4d6b676b1ea686673b84c5a920343c2df6ac3867798cd0", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "769b4bb4ae9e190fb51f5a658a831fd91748a6c57bcea9883cc669ea1eb17aa1", "generation_seconds_batch": 18.267224235925823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.074678421020508, "target_z": 1.9218748610504095, "ce": 6.23706579208374, "genuineness": 4.024092197418213, "identity": 0.7389810085296631, "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_Concentration/858bfba40c0aab783a4d6b676b1ea686673b84c5a920343c2df6ac3867798cd0.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "85a301a0f88aa52a24ad5491224f98c9a6ec1d5af291b8abea3109424f218ca4", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "1cebfc164b19224040911e36bf1820caa307360f3d97ee7c2a8c96841fff4cf8", "generation_seconds_batch": 18.103598022949882, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7950024604797363, "target_z": 1.539062651059876, "ce": 6.268836498260498, "genuineness": 4.256305694580078, "identity": 0.5366591215133667, "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_Concentration/85a301a0f88aa52a24ad5491224f98c9a6ec1d5af291b8abea3109424f218ca4.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "86239001ddb650c0a88ccf23279fdae75790a107a4b42440bd446f4ed85aa813", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d28265c6e03445ff37087fb0cab4b650d67a47746f43d08738d1943ea9a3b0c3", "generation_seconds_batch": 18.34578769793734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7093873023986816, "target_z": 1.4218751465981918, "ce": 5.295859336853027, "genuineness": 4.293961524963379, "identity": 0.6620174050331116, "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_Concentration/86239001ddb650c0a88ccf23279fdae75790a107a4b42440bd446f4ed85aa813.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "869db6fcb46f6eedc2340ca5c8692fadf89025fef176c3f87998ed02a94d1928", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c104d92af7cfca0aabaa63e324c942c1cc9f70171339abf50e61523f4f1b52dc", "generation_seconds_batch": 22.54989518702496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0975091457366943, "target_z": 1.9531248839962134, "ce": 6.125868320465088, "genuineness": 4.400654315948486, "identity": 0.7808934450149536, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise.", "wer": 0.3333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/869db6fcb46f6eedc2340ca5c8692fadf89025fef176c3f87998ed02a94d1928.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "87eb8d0162be2b235def65d518def5ca2b95db6facf574b7c1b31761ec6db91f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "0e823d4cea91e62175f7343ba21a60b20fdc44721be3de6768a1a3c43ea303d9", "generation_seconds_batch": 17.654171422007494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0061864852905273, "target_z": 1.8281251185533203, "ce": 6.125868320465088, "genuineness": 4.607763767242432, "identity": 0.36812523007392883, "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_Concentration/87eb8d0162be2b235def65d518def5ca2b95db6facf574b7c1b31761ec6db91f.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "88b633b5fc03e7dd93f855bb530c97a2845dd637c9806ed4621414f96be5c752", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6415cf6d7a52b274411c40b153dff48c40e2f26e7ddc9c75851f86656f7d4981", "generation_seconds_batch": 23.15541494905483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0404324531555176, "target_z": 1.874999989801865, "ce": 6.165581703186035, "genuineness": 4.20609712600708, "identity": 0.7573622465133667, "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_Concentration/88b633b5fc03e7dd93f855bb530c97a2845dd637c9806ed4621414f96be5c752.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "890911ae3299affe811ffc32e7d0db7be352c749d4e7d777bffc4013a7767a22", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "31f41f0f211df0701a20156f568c2ddf80fe9657ca85a651ff2d8bd807913533", "generation_seconds_batch": 22.78584594395943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8692021369934082, "target_z": 1.6406249808784967, "ce": 5.982900142669678, "genuineness": 4.469690799713135, "identity": 0.679126501083374, "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_Concentration/890911ae3299affe811ffc32e7d0db7be352c749d4e7d777bffc4013a7767a22.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "8916d2783469de8268e838ee089db9a03e55306a531b420130ed2f4951cff2f3", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "470788da33d7d5414bd098071928806c9714a73a486d288e4ed63fa55c892c56", "generation_seconds_batch": 23.72659680491779, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.091801643371582, "target_z": 1.9453126230150044, "ce": 5.998785495758057, "genuineness": 4.268857479095459, "identity": 0.8213070631027222, "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_Concentration/8916d2783469de8268e838ee089db9a03e55306a531b420130ed2f4951cff2f3.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "892d08ecd1584dd06e580cedb18f3b9d0daf9b7dd5e7b03b58c396d805a76370", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "be7040a520732525e1250edaa13357172cbd41d5f65704c080f5351f16d55638", "generation_seconds_batch": 22.013855537050404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7208025455474854, "target_z": 1.4374999949009324, "ce": 6.09409761428833, "genuineness": 4.2751336097717285, "identity": 0.4263290762901306, "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_Concentration/892d08ecd1584dd06e580cedb18f3b9d0daf9b7dd5e7b03b58c396d805a76370.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "894db7d19b3280a7fa3c7ae13283a5117c5cc0db1ebf6404835b3190d903af32", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "9b82f975a331b98e642a5c5f7c492d8260aa9c4729799ad7e89f1c4587e17f40", "generation_seconds_batch": 18.26435303094331, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.029017210006714, "target_z": 1.8593751414991242, "ce": 5.871703147888184, "genuineness": 4.582659721374512, "identity": 0.551815390586853, "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_Concentration/894db7d19b3280a7fa3c7ae13283a5117c5cc0db1ebf6404835b3190d903af32.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "8952fb52c4832acc3ad42066ac6714c64924a279a7047cca3c152c95f938eea2", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "9207ee63f3e07637cf0aec4f2989c95025f6c81a1ffd458a97b4511c18d38b4a", "generation_seconds_batch": 23.228264773031697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0860939025878906, "target_z": 1.9375000356934728, "ce": 5.80021858215332, "genuineness": 4.13078498840332, "identity": 0.5928148031234741, "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_Concentration/8952fb52c4832acc3ad42066ac6714c64924a279a7047cca3c152c95f938eea2.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "8974d24c6c6b2d270cde7f1cbe1b8756880b27c24a2d22d7686a28cbb460e0d7", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "33a0b1a91e8e2e5b28c91ec954b29073fb889a944e82bc09f9e355a9c0dca6bc", "generation_seconds_batch": 21.80029243498575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.880617618560791, "target_z": 1.6562501555215599, "ce": 5.927301406860352, "genuineness": 4.482243061065674, "identity": 0.6624757647514343, "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_Concentration/8974d24c6c6b2d270cde7f1cbe1b8756880b27c24a2d22d7686a28cbb460e0d7.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "89987d26705268312f47f2b915d73dcad34d433f100807e641800b30b557029b", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "faea8896b956e8d86c4d96bae874938e3cbfb057fa1868f71da340b6a3b0e5e6", "generation_seconds_batch": 24.874171786941588, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7550485134124756, "target_z": 1.4843748661494771, "ce": 6.308549880981445, "genuineness": 4.457139015197754, "identity": 0.5398853421211243, "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_Concentration/89987d26705268312f47f2b915d73dcad34d433f100807e641800b30b557029b.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "89b0f905cc3685b10bd41da9ee462d583d7e73bcfc30d769ec0f30e30a812b8c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "ebf7a89707daf247108c604321d113e633ad8131a0831265df66d8a0d61c48c2", "generation_seconds_batch": 22.869742520037107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7025229930877686, "target_z": 2.781250002549534, "ce": 5.911416053771973, "genuineness": 4.256305694580078, "identity": 0.5865602493286133, "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_Concentration/89b0f905cc3685b10bd41da9ee462d583d7e73bcfc30d769ec0f30e30a812b8c.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": "89c9a2b32a0956f9666178caf2fd0d060e1b5dfe79a01b2e1c15022b01b8eae9", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "134a1837a6889e8d02705c79f285aed091ca250783f39f885b818a41f88d811f", "generation_seconds_batch": 17.085949030006304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4171390533447266, "target_z": 2.390624878897146, "ce": 5.816103935241699, "genuineness": 4.143336772918701, "identity": 0.5745739936828613, "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_Concentration/89c9a2b32a0956f9666178caf2fd0d060e1b5dfe79a01b2e1c15022b01b8eae9.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "89f32eab37422352ae5bc6883eb14192f5c4965a96fb417195847112ba5ca796", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "740040d940f4033f46c1f47ce7af1236dc22323dd8aaf07a111c0a0b7dc5ba3b", "generation_seconds_batch": 25.67511607997585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7550485134124756, "target_z": 1.4843748661494771, "ce": 6.316492557525635, "genuineness": 4.482243061065674, "identity": 0.4094708561897278, "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_Concentration/89f32eab37422352ae5bc6883eb14192f5c4965a96fb417195847112ba5ca796.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "8ab1a7f31f038e7364cfa4213081dc48b6339e095004935839cabad2a3f70d99", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "f3ee1f8fb98d77a809f74895597e969bd12036e5a02eedaba0440030f7d097a6", "generation_seconds_batch": 18.458772829035297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8007099628448486, "target_z": 1.546874912041085, "ce": 6.268836498260498, "genuineness": 4.055472373962402, "identity": 0.711135983467102, "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_Concentration/8ab1a7f31f038e7364cfa4213081dc48b6339e095004935839cabad2a3f70d99.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "8b35958fdfe6426ac03a794852ede9d86ad433b3a835fe1da68c5e42b56e0f75", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "2e53eddee58bae1bb2a0d507304659795d3733887414e1c48c750781ff7d32fa", "generation_seconds_batch": 21.92331942601595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.926278829574585, "target_z": 1.7187498750728454, "ce": 6.149696350097656, "genuineness": 4.595211505889893, "identity": 0.6479876041412354, "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_Concentration/8b35958fdfe6426ac03a794852ede9d86ad433b3a835fe1da68c5e42b56e0f75.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "8b3afac85b09d6d4046fba780a1e1ebbc3f5e05d1d8ba780ff3bfc38400698d8", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "6c7b773c1b9907521bfe2a6d233a28f4ba0cebb38abbda9574304c18d5171ff0", "generation_seconds_batch": 22.634524176013656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.439969778060913, "target_z": 2.42187490184295, "ce": 6.078212261199951, "genuineness": 4.406930446624756, "identity": 0.6136477589607239, "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_Concentration/8b3afac85b09d6d4046fba780a1e1ebbc3f5e05d1d8ba780ff3bfc38400698d8.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": "8b40f4608f62de22d52476582dbd7fa475242f7281dd1cde59ed1b4fb18c5119", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "156335d4b9044ed95aecd5ffa9547baab378ae404002dbcd6b0515acb524b8b4", "generation_seconds_batch": 17.963124723057263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2002475261688232, "target_z": 2.0937501504224922, "ce": 5.927301406860352, "genuineness": 4.243753433227539, "identity": 0.45047110319137573, "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_Concentration/8b40f4608f62de22d52476582dbd7fa475242f7281dd1cde59ed1b4fb18c5119.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "8b4cc39a2a4ff022e61725ed7cf36ef03e1e719c004cf91ea271c26bb4cc3ca5", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4665bdb897414c9e0c888c5349122b5a227193d0d6e872514ea38ed915ef09fc", "generation_seconds_batch": 23.77342069603037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6865565776824951, "target_z": 1.3906251236523879, "ce": 6.022613525390625, "genuineness": 4.482243061065674, "identity": 0.5709075927734375, "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_Concentration/8b4cc39a2a4ff022e61725ed7cf36ef03e1e719c004cf91ea271c26bb4cc3ca5.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "8c2dd4f9034b8257f96cd69a6321e507cc940334cbd422b181ba202393c20d70", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "401b8b37e5ef85ddbd17a054b44a4b258dec12f000420cbec40cd2c826b40ead", "generation_seconds_batch": 23.768282996024936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2584807872772217, "target_z": 0.8046876013439673, "ce": 6.284721851348877, "genuineness": 4.582659721374512, "identity": 0.4624674916267395, "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_Concentration/8c2dd4f9034b8257f96cd69a6321e507cc940334cbd422b181ba202393c20d70.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": "8c9a7c07c72d2ec4b790424026f4c7669b4de656501e035dd4fd24ed607a0c58", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd937a8dd43dc0b106148e561ad6767074e8b6dbed7be3a52d88440812c880ac", "generation_seconds_batch": 15.142117582028732, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0118939876556396, "target_z": 1.8359373795345293, "ce": 5.95112943649292, "genuineness": 4.413206577301025, "identity": 0.7283298969268799, "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_Concentration/8c9a7c07c72d2ec4b790424026f4c7669b4de656501e035dd4fd24ed607a0c58.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "8ce7711f5c104c04283f87805948f33c2b741d848ff512ff98bc9de254eefbe1", "bucket": "emo_Concentration", "phase": "wording", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "fba19660faef1c49c510f84b2a100c8bf8c129da121d942c2d01ec42d86f39dd", "generation_seconds_batch": 18.068687148042955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1431705951690674, "target_z": 2.0156249298878213, "ce": 6.165581703186035, "genuineness": 4.356721878051758, "identity": 0.6347377300262451, "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_Concentration/8ce7711f5c104c04283f87805948f33c2b741d848ff512ff98bc9de254eefbe1.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": "8d72517510cf9753bada0fa1ed6c9cdea97b332183fcecc5191d971abc314ef0", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6092e8f95c4dca08959e63bfadeef2144430a96af86076de55ae030db01e162c", "generation_seconds_batch": 23.264406607020646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7950024604797363, "target_z": 1.539062651059876, "ce": 6.419747352600098, "genuineness": 4.432034492492676, "identity": 0.6536852717399597, "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_Concentration/8d72517510cf9753bada0fa1ed6c9cdea97b332183fcecc5191d971abc314ef0.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "8e1f8f4fb25dfce56ae7c400a9b7ebb160bed3850a4971f46249c197aad90e28", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "205e3421dd9ffbf468aac5ceaf5035efc69563322acf5c4262b15e7ef55dc4d0", "generation_seconds_batch": 22.06708541198168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8692021369934082, "target_z": 1.6406249808784967, "ce": 5.927301406860352, "genuineness": 4.6956281661987305, "identity": 0.791290819644928, "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_Concentration/8e1f8f4fb25dfce56ae7c400a9b7ebb160bed3850a4971f46249c197aad90e28.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "8e2a00ed41c72e5a48415da3e74a30c524e4acef2da7280c3d33f3814ed6b65a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "8d1d344d0e3f9178adff0e153b2feffa3067bb890d42c0f92681aa638b740dad", "generation_seconds_batch": 23.77896605001297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.029017210006714, "target_z": 1.8593751414991242, "ce": 5.863759994506836, "genuineness": 4.570107460021973, "identity": 0.7332777976989746, "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_Concentration/8e2a00ed41c72e5a48415da3e74a30c524e4acef2da7280c3d33f3814ed6b65a.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "8e5fc46f6665db0cbbac226fd66ec867e8f433177cd8b10b5e183b4e39c081fd", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "ecba2e07226821db3a35f5a6ee0fb979c9077c7810a917a3d6dabef3b2795840", "generation_seconds_batch": 24.511546889087185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.732217788696289, "target_z": 1.4531248432036732, "ce": 5.720792293548584, "genuineness": 4.821148872375488, "identity": 0.7668664455413818, "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_Concentration/8e5fc46f6665db0cbbac226fd66ec867e8f433177cd8b10b5e183b4e39c081fd.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "8f2301ecdffd1e9bd13a8881a82a56337fb42511d6652f1a74f55657d0e52437", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b95351834c503cd7c3ab09b30ad55b2ac20547e9d5a307312d38bd353841dfd5", "generation_seconds_batch": 22.93632545194123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8235406875610352, "target_z": 1.5781249349868889, "ce": 6.133810997009277, "genuineness": 4.7332844734191895, "identity": 0.8584167957305908, "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_Concentration/8f2301ecdffd1e9bd13a8881a82a56337fb42511d6652f1a74f55657d0e52437.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": "8f63f88d943e3bf1b2756755f3a4b63ae792aebe46ffbc20abf135e32aa82a3d", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "780a6d8069d90cb8d2cb62ee0283be596a80cbe7a645f682a0f0024f48f51eb3", "generation_seconds_batch": 16.130910932086408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3144009113311768, "target_z": 2.2499999388111895, "ce": 5.780362129211426, "genuineness": 4.7081804275512695, "identity": 0.4475230574607849, "hypothesis": "I create the numerous l envelope. Lise le bien and verify the two derivatives. Appelle moi when you have a moment.", "wer": 0.7727272727272727, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/8f63f88d943e3bf1b2756755f3a4b63ae792aebe46ffbc20abf135e32aa82a3d.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "8fdc7d43d86109149d3067b16364e36b87283bfdd28bc947fe1705229bda4f4c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "341eef64d0ae025d840f5d6dc0de16f8577d968b7eddd97a52782fb22f57e17b", "generation_seconds_batch": 23.711970569915138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8634943962097168, "target_z": 1.6328123935569652, "ce": 6.117925643920898, "genuineness": 4.582659721374512, "identity": 0.659415602684021, "hypothesis": "He can entrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "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_Concentration/8fdc7d43d86109149d3067b16364e36b87283bfdd28bc947fe1705229bda4f4c.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": "90fba7d7980f837ab369d29397fb69a009943757f21691a3fafca3acb3dd7283", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "cb103dbc0c949778216effca409dc2676bdfd1cb1c8cef36044befde8b1eb798", "generation_seconds_batch": 18.089347754023038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9434020519256592, "target_z": 1.74218763703744, "ce": 5.8875885009765625, "genuineness": 4.532451152801514, "identity": 0.259000688791275, "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": 0.120000000000001, "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_Concentration/90fba7d7980f837ab369d29397fb69a009943757f21691a3fafca3acb3dd7283.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "91127cb2e91af641472ff7cf751d7fb6fc64c58ac39302664073711da46972ff", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "1f33cd0c9b77522678b00f1b8d0ced16810393e39fe91876445adb115693bab2", "generation_seconds_batch": 15.067032163962722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.789294719696045, "target_z": 1.5312500637383442, "ce": 5.673136234283447, "genuineness": 4.444586753845215, "identity": 0.7777303457260132, "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_Concentration/91127cb2e91af641472ff7cf751d7fb6fc64c58ac39302664073711da46972ff.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "913ed3f60c4f3d1608f11266946620cef587849b107d8d4c2d0e8628d99decdb", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fc0cb4bdc6416cb9340009a81a4ed9aa0d12b3978efb017330963c1b1f8fdf7c", "generation_seconds_batch": 16.493485787068494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0518476963043213, "target_z": 1.8906248381046056, "ce": 6.109982967376709, "genuineness": 3.9173994064331055, "identity": 0.28801417350769043, "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_Concentration/913ed3f60c4f3d1608f11266946620cef587849b107d8d4c2d0e8628d99decdb.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": "914e778870ca6f24b4e508452bcea34c497a8f0a6ae623a8a7203148fc9391d7", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ed248dff513abb6ea8d72808f2f7fe60f3f4747f83c897dff59a89ba89f2e147", "generation_seconds_batch": 23.667125103995204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0449836254119873, "target_z": 3.25000002039627, "ce": 6.165581703186035, "genuineness": 3.860914945602417, "identity": 0.6014846563339233, "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_Concentration/914e778870ca6f24b4e508452bcea34c497a8f0a6ae623a8a7203148fc9391d7.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "916434f45fa393a77dd0aee2d0f2b3532cb95d578109430f46158d5f91fec038", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "e19bd14fba42062adfb7a497ed5d015d22df5306cf7715ea106eea1342ef2e5e", "generation_seconds_batch": 23.548990524024703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9319865703582764, "target_z": 1.726562462394377, "ce": 6.0305562019348145, "genuineness": 4.15588903427124, "identity": 0.5959709286689758, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/916434f45fa393a77dd0aee2d0f2b3532cb95d578109430f46158d5f91fec038.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "91decc03167b725bbc59ea0b6548cd84687f93356ad9de4fe2a688618646a93c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "7fb4f763c0d5563df453a4a67d1456670c26d92752c48ac1c55048921b78b45b", "generation_seconds_batch": 22.131983369006775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9605250358581543, "target_z": 1.7656250726617124, "ce": 6.070269584655762, "genuineness": 4.425758361816406, "identity": 0.8180249929428101, "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_Concentration/91decc03167b725bbc59ea0b6548cd84687f93356ad9de4fe2a688618646a93c.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": "9289e9b47530e8e567ac7290727afc2ad6d515194f445054406d03aae3a775b2", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b6382526cabf97c3125ff93ea9874d9b935cd64addaef9c1fc8d2ba5b3ac3ac8", "generation_seconds_batch": 23.854426486999728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.211662769317627, "target_z": 2.109374998725233, "ce": 6.086154937744141, "genuineness": 4.306513786315918, "identity": 0.6509824991226196, "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_Concentration/9289e9b47530e8e567ac7290727afc2ad6d515194f445054406d03aae3a775b2.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "92fea53dd1c47ddb8bd9aee2ecc8d60a2be946f56592afddd36aad8b845ecfa5", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "482658601a1154db06a1dc3d9271170c5802bdfb0c7b041ecbb33bc2fbfadd60", "generation_seconds_batch": 24.821697078994475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.245908737182617, "target_z": 2.1562498699737778, "ce": 5.689021587371826, "genuineness": 4.356721878051758, "identity": 0.27207595109939575, "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_Concentration/92fea53dd1c47ddb8bd9aee2ecc8d60a2be946f56592afddd36aad8b845ecfa5.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "932962cd613365a8c242a2fc1b2d610beb78d64b82058068c1c69cab4e0b5ff5", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "00b0a3340b255364ee4566a7c99b318610d07cc0577095c85c176c56915cabf6", "generation_seconds_batch": 23.275602945010178, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7550485134124756, "target_z": 1.4843748661494771, "ce": 6.268836498260498, "genuineness": 4.632867813110352, "identity": 0.6525335311889648, "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_Concentration/932962cd613365a8c242a2fc1b2d610beb78d64b82058068c1c69cab4e0b5ff5.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "9361e5474a0e07cc96189954323ef245e171d61524adbd5cd1d8a0b7445ce909", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "9bd6767205f0557d1258dee5405f9d3914cff2423125ae98a9f46b4bb37add37", "generation_seconds_batch": 22.504525715019554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2915701866149902, "target_z": 2.2187499158653856, "ce": 5.748591423034668, "genuineness": 4.268857479095459, "identity": 0.42473331093788147, "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_Concentration/9361e5474a0e07cc96189954323ef245e171d61524adbd5cd1d8a0b7445ce909.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "936c35db22cae7113cf2744e8af11d7a136f23a258edecd0ac308ffc4a598328", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "e05c4134fbe47b19eaa8c39ddb655c9fdbc937e8f48b4cd6ff8021e53a6b158e", "generation_seconds_batch": 21.02810282295104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9034481048583984, "target_z": 1.6874998521270415, "ce": 5.919358730316162, "genuineness": 4.319066047668457, "identity": 0.8014675974845886, "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_Concentration/936c35db22cae7113cf2744e8af11d7a136f23a258edecd0ac308ffc4a598328.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "938d8df0316f13956caa0615866529a78aa3149eaf65f22a32a80fd098b156c7", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "a2863001babdf847da1e072d09194ede62ac26885c5bc3d2f911e668bc31a9a1", "generation_seconds_batch": 18.536726046935655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.39430832862854, "target_z": 2.359374855951342, "ce": 6.054384231567383, "genuineness": 4.2249250411987305, "identity": 0.6057206392288208, "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_Concentration/938d8df0316f13956caa0615866529a78aa3149eaf65f22a32a80fd098b156c7.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "93a3945b8ea4f507af30a895b115bbbd367bef3f2023f1a263f596d228b485f3", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "603cf75f1a84a38838d0d23af970b5d3f18efb1b360331018f422694a9483cd9", "generation_seconds_batch": 22.54989518702496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.120339870452881, "target_z": 1.9843749069420173, "ce": 5.903473377227783, "genuineness": 4.7332844734191895, "identity": 0.7156144380569458, "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_Concentration/93a3945b8ea4f507af30a895b115bbbd367bef3f2023f1a263f596d228b485f3.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "93ee54ce9e5de27f4307a87d5ff1b8c7663b49c883353e7d8263a7da86d4b52e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "69c27ee6c221444e0f7bedf1129428660281c956f66e6cd649c18a6e67454914", "generation_seconds_batch": 23.016443202039227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.063263177871704, "target_z": 1.906250012747669, "ce": 6.09409761428833, "genuineness": 4.444586753845215, "identity": 0.7182049751281738, "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_Concentration/93ee54ce9e5de27f4307a87d5ff1b8c7663b49c883353e7d8263a7da86d4b52e.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "94485be157c7139bb47d32312b2cffcd163316aaa84a7681629ceae69cc46fed", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "5e6aad7b62e12539958f1d0e9a36445c064419d72ffd60615210c80d23ec5380", "generation_seconds_batch": 16.897414582083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9148635864257812, "target_z": 1.7031250267701046, "ce": 6.117925643920898, "genuineness": 4.469690799713135, "identity": 0.5883200168609619, "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_Concentration/94485be157c7139bb47d32312b2cffcd163316aaa84a7681629ceae69cc46fed.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "9501c3cdef0e0dfd66afb4a82a1ce12c856b2aaaab56ceaf506da5b368b8e0c7", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3832601f9eda1b946702c11f427eaa2ec6006c20f0fe47bd35e22b4ccf5baee5", "generation_seconds_batch": 18.010416439035907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.595233678817749, "target_z": 1.2656250318691722, "ce": 6.1894097328186035, "genuineness": 4.6203155517578125, "identity": 0.319768488407135, "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_Concentration/9501c3cdef0e0dfd66afb4a82a1ce12c856b2aaaab56ceaf506da5b368b8e0c7.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "95cd9113e816571d8399e4886ecc188f67491ae7f3448e4baef59cf176618097", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3a24fbae5d7a16a09fe0bc5a0213ec8b99f9e8283fa50a5126b5f24cbc5e8603", "generation_seconds_batch": 23.454739641980268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2584807872772217, "target_z": 0.8046876013439673, "ce": 6.268836498260498, "genuineness": 4.494794845581055, "identity": 0.26282596588134766, "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_Concentration/95cd9113e816571d8399e4886ecc188f67491ae7f3448e4baef59cf176618097.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "96111e1677051218573396c872ca84d24ae733cfe26bde00c033b909fda7d6da", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "8278eadd2a6f1c3a8dfb2d08994d0f191c001332d04dbfb101e49a3968cc5134", "generation_seconds_batch": 23.783317293971777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0404324531555176, "target_z": 1.874999989801865, "ce": 5.903473377227783, "genuineness": 4.482243061065674, "identity": 0.7949179410934448, "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_Concentration/96111e1677051218573396c872ca84d24ae733cfe26bde00c033b909fda7d6da.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": "9625085f22a936d344b38054187538e927d8f92348ab1936b7e1e50587f412bc", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "53573ab5413ff9792f458063381b96639a2da7fe3198fe8df38df0a02c850c89", "generation_seconds_batch": 20.131772657041438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6911075115203857, "target_z": 2.7656248279064704, "ce": 6.221180438995361, "genuineness": 3.9676074981689453, "identity": 0.5386887788772583, "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_Concentration/9625085f22a936d344b38054187538e927d8f92348ab1936b7e1e50587f412bc.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "962aca727842aa13f51f297cfe8d2e2cedd47cf2947322a2a049138710f0b1ef", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "2cd289841e7388500453a2ff0e58b597d671b6395146452808af2a78b2382a3f", "generation_seconds_batch": 23.73834825702943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.091801643371582, "target_z": 1.9453126230150044, "ce": 6.316492557525635, "genuineness": 3.8797430992126465, "identity": 0.5998924374580383, "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_Concentration/962aca727842aa13f51f297cfe8d2e2cedd47cf2947322a2a049138710f0b1ef.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "973f0004b74d369c2fb3653b0590d424d51fd7d7253140569247430ef791599f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "2be6a700cde79cb8c27bdd48ca0b85854f7ebb73344f14b765ee88808004e48e", "generation_seconds_batch": 22.786992094945163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.503910779953003, "target_z": 1.1406249400859565, "ce": 6.332377910614014, "genuineness": 4.482243061065674, "identity": 0.6044577360153198, "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_Concentration/973f0004b74d369c2fb3653b0590d424d51fd7d7253140569247430ef791599f.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": "9757964d17e7e603340964c7b2ccf3b9539f0970d44870b09c068a7d35737127", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0138a086bc9a8abb474816844ebf9e091071aadcdd9012ea00982229cd605228", "generation_seconds_batch": 23.02806291601155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8577868938446045, "target_z": 1.625000132575756, "ce": 6.38003396987915, "genuineness": 4.3881025314331055, "identity": 0.5640515089035034, "hypothesis": "Die Schlüss 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_Concentration/9757964d17e7e603340964c7b2ccf3b9539f0970d44870b09c068a7d35737127.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": "97ceecebcb02305df1ede491bdbf0b21503807da4355d89f4983f7214e14a1f0", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "beb2d59e8f32a4bb13bbf127b1a8f650b722d9ec894f49663ea448d18db28f72", "generation_seconds_batch": 23.667125103995204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9422454833984375, "target_z": 3.109375080310314, "ce": 6.23706579208374, "genuineness": 4.1998209953308105, "identity": 0.5225631594657898, "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_Concentration/97ceecebcb02305df1ede491bdbf0b21503807da4355d89f4983f7214e14a1f0.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "97e0af7151bc82a4f7dca28871184948c0dbe0999ebb586a80a524533c7668c8", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a80cc619c4571d1959f49f271a1714312daef5f8e126845732c290c3d92be6e4", "generation_seconds_batch": 24.529771529021673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5838183164596558, "target_z": 1.2500000203962702, "ce": 6.078212261199951, "genuineness": 4.444586753845215, "identity": 0.3177874982357025, "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_Concentration/97e0af7151bc82a4f7dca28871184948c0dbe0999ebb586a80a524533c7668c8.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "9815d4b24dbea53bda15cf2084b4fe8d5e8849ce5d94e586c3b55ea85dfe2b82", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "05842e1ace9f19c357c1635e10e1b908d038479d638a217a22d67c0dd950eb23", "generation_seconds_batch": 23.422360270982608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9605250358581543, "target_z": 1.7656250726617124, "ce": 5.4944257736206055, "genuineness": 4.519899368286133, "identity": 0.6038140654563904, "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_Concentration/9815d4b24dbea53bda15cf2084b4fe8d5e8849ce5d94e586c3b55ea85dfe2b82.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": "991f53c8cb49b723cef1043d2eee69c7dc4c1449ebce81e1f047e12d004ffd52", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "838bb7843d7ec4c6f834c1af9e3110300d5d976103f6c43d3e7ec83538814d06", "generation_seconds_batch": 16.959682912915014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9034481048583984, "target_z": 1.6874998521270415, "ce": 6.3641486167907715, "genuineness": 4.3127899169921875, "identity": 0.6225545406341553, "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_Concentration/991f53c8cb49b723cef1043d2eee69c7dc4c1449ebce81e1f047e12d004ffd52.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "991f640e6706b43e3d52692ca0430e11b7c5bbf1cb531cc4e35e759e798cbda0", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5a22dcdaec5c61768b92710e8c05361721da88ead02c33e06b507dd18038335b", "generation_seconds_batch": 16.985800566966645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9491095542907715, "target_z": 1.7499998980186493, "ce": 6.086154937744141, "genuineness": 4.457139015197754, "identity": 0.7791257500648499, "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_Concentration/991f640e6706b43e3d52692ca0430e11b7c5bbf1cb531cc4e35e759e798cbda0.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "99957be92a1b5b327a147805d7b288d146bf86d6275fcb6e7b91dee398b4f6d9", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 126, "seconds_generated": 10.08, "mp3_sha256": "fdcd2d2eb3242639193f184292a1afdcd37e48fb74dd1877c7ed4f47793874e4", "generation_seconds_batch": 25.90532326803077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7664639949798584, "target_z": 1.5000000407925402, "ce": 4.8384108543396, "genuineness": 4.20609712600708, "identity": 0.3695550262928009, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos.", "wer": 0.23529411764705882, "duration_error_s": 0.11999999999999922, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/99957be92a1b5b327a147805d7b288d146bf86d6275fcb6e7b91dee398b4f6d9.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "172ad2dcdd2e820ba2e7cc3ba2ef4573b2cf536116b01c50d3d2547c163b7311", "generation_seconds_batch": 18.221175000071526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2813113927841187, "target_z": 0.83593746111961, "ce": 6.284721851348877, "genuineness": 4.7081804275512695, "identity": 0.6460624933242798, "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_Concentration/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "99fd024e067138c29c7fb06336ee04e7fced4f009fac750011dbd1c615a4f689", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d2c27bef6bee5ce16424224b0089655173237a48c93030f49a60df1017b876ef", "generation_seconds_batch": 23.747077136998996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0518476963043213, "target_z": 1.8906248381046056, "ce": 6.24500846862793, "genuineness": 4.281409740447998, "identity": 0.6173210144042969, "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_Concentration/99fd024e067138c29c7fb06336ee04e7fced4f009fac750011dbd1c615a4f689.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "9a34cb5a240a0be5358614ff788e7fcaf6ea2a2baa1ffd58e88feb0c2e9fef82", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "37eee8010f8197426981625a1dbb3569d43aee1c3abfd49b2094371fa291519d", "generation_seconds_batch": 17.474679620936513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5153262615203857, "target_z": 1.1562501147290196, "ce": 6.292664527893066, "genuineness": 4.507347106933594, "identity": 0.47856247425079346, "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_Concentration/9a34cb5a240a0be5358614ff788e7fcaf6ea2a2baa1ffd58e88feb0c2e9fef82.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "9a8828ba80db498263a8e880546bdb268acf7dad3ad51f8977c7802676484c1d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "455fd9e571834c6b752778361830336e3f5089e8041a30115dbba562e4d7c5ef", "generation_seconds_batch": 24.329404892981984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.000478744506836, "target_z": 1.8203125312317887, "ce": 6.141753673553467, "genuineness": 4.532451152801514, "identity": 0.5443795919418335, "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_Concentration/9a8828ba80db498263a8e880546bdb268acf7dad3ad51f8977c7802676484c1d.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "9ad9ee7085a3089f2f78abc6e0c2d8a5334f2b13ad0a525928802b21c98bd50a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "388c540dd5f92b57b5caaf31113137fbd66675432d1be581ed79564bb86bb49f", "generation_seconds_batch": 16.742083896999247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8692021369934082, "target_z": 1.6406249808784967, "ce": 6.197352409362793, "genuineness": 4.519899368286133, "identity": 0.6035037040710449, "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_Concentration/9ad9ee7085a3089f2f78abc6e0c2d8a5334f2b13ad0a525928802b21c98bd50a.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "9b84563538a6b69fa0578e97fe563ac1297241aa00a48c0222ce5ff5983d3c2b", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "695115f0e8e174a72035d750c9326dc8af3d63816000f3b8d1eeb5f166a41cfc", "generation_seconds_batch": 23.938474473077804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9434020519256592, "target_z": 1.74218763703744, "ce": 5.561938762664795, "genuineness": 3.961331605911255, "identity": 0.5041623115539551, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/9b84563538a6b69fa0578e97fe563ac1297241aa00a48c0222ce5ff5983d3c2b.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "9bb55f464b8fd680f4cdbcd69b031a9266ac1f7f171f9fab12668241bfbba352", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "55a1972c8c57c5b5e13035d97a4c2234da4ffa6e62f16ae2cf1ff2d24d110050", "generation_seconds_batch": 23.889214066090062, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9491095542907715, "target_z": 1.7499998980186493, "ce": 6.078212261199951, "genuineness": 4.607763767242432, "identity": 0.804389476776123, "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_Concentration/9bb55f464b8fd680f4cdbcd69b031a9266ac1f7f171f9fab12668241bfbba352.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "0fe1b30b13c797036e2de03a3b8d7405a9647904a760808ed7e972311e847605", "generation_seconds_batch": 18.28961330105085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0518476963043213, "target_z": 1.8906248381046056, "ce": 6.260893821716309, "genuineness": 4.369274139404297, "identity": 0.7745356559753418, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier, naast de hoge boekenkast. We zetten het na de lunch terug.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "9c2413d04670065a0644d893584ac6c0f92c989b7d18928cc0c3c5493b0257b5", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "decbc949d158dab0e1b6e6558f6018b57b8909446775eb5cb85d25df54812746", "generation_seconds_batch": 22.657137342030182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.063263177871704, "target_z": 1.906250012747669, "ce": 6.324435234069824, "genuineness": 4.15588903427124, "identity": 0.6167236566543579, "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_Concentration/9c2413d04670065a0644d893584ac6c0f92c989b7d18928cc0c3c5493b0257b5.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "4e23fe73f8282cd728fb73303557dd130163b7f61ff2409f0fbe179d4a9c4e01", "generation_seconds_batch": 18.12405549606774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0518476963043213, "target_z": 1.8906248381046056, "ce": 5.998785495758057, "genuineness": 4.394378662109375, "identity": 0.6264249682426453, "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_Concentration/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "9dc2ea5c277fec094eac473e1e425efef2ae164dcf030dc2023a53f0895b4f75", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "7a2fa7913c9de66a6b85559f15d197da085e122570e5a0308e41cfc937565a63", "generation_seconds_batch": 23.68077501305379, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.834956169128418, "target_z": 1.593750109629952, "ce": 6.125868320465088, "genuineness": 4.419482707977295, "identity": 0.5989919900894165, "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_Concentration/9dc2ea5c277fec094eac473e1e425efef2ae164dcf030dc2023a53f0895b4f75.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "9e78f34e0118977726f555e32f1a6d912099499cee3a38b9dc71716e558088e4", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "b3f4770638ced8528dd49020b696e885382f679ae01d98f3f9b937ac8264e999", "generation_seconds_batch": 22.773432394023985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.549572229385376, "target_z": 1.2031249859775643, "ce": 6.427689552307129, "genuineness": 4.300237655639648, "identity": 0.40539538860321045, "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_Concentration/9e78f34e0118977726f555e32f1a6d912099499cee3a38b9dc71716e558088e4.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "9ec770f83314ade71399205d20c4bc5faafa395c100d9150a51b7ca56ab69576", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d30bf513ff214b0cca7f06e74df91f2a3cf4921e8ff86c7e593a6b0b81ba3b5c", "generation_seconds_batch": 23.26672536402475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.36006236076355, "target_z": 2.3124999847027974, "ce": 5.982900142669678, "genuineness": 4.231201171875, "identity": 0.6857413053512573, "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_Concentration/9ec770f83314ade71399205d20c4bc5faafa395c100d9150a51b7ca56ab69576.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "9ee3aa74b67f2e4973b7cbf662310b2b488deb1413b4693fe01041c4d655bbef", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "96ad457805c6d0783cb18e541f6ceae66b4cbb8bc8b711bd6bb6ed246da8134d", "generation_seconds_batch": 21.746081555029377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9491095542907715, "target_z": 1.7499998980186493, "ce": 5.262103080749512, "genuineness": 4.300237655639648, "identity": 0.7461118102073669, "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_Concentration/9ee3aa74b67f2e4973b7cbf662310b2b488deb1413b4693fe01041c4d655bbef.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": "a024f9f0f9068137ffaa10f6f548907646e6bb5e17ec61fc6171a2502f2fe304", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f76945d76ea77b920b64cb7b9531569fbd51f8d4074b3693dd82c9b2b47f0567", "generation_seconds_batch": 17.619504275964573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7664639949798584, "target_z": 1.5000000407925402, "ce": 6.284721851348877, "genuineness": 4.482243061065674, "identity": 0.23170159757137299, "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_Concentration/a024f9f0f9068137ffaa10f6f548907646e6bb5e17ec61fc6171a2502f2fe304.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "a075e9fb61af20c8af787d11b0664db402ff882da57b93a650315898d01ed0da", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "1bb86033f6dd762a34a002cd33c1612b0668033ee540881c6a4346888b2f1b1c", "generation_seconds_batch": 17.72492313804105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0518476963043213, "target_z": 1.8906248381046056, "ce": 5.967014789581299, "genuineness": 4.13078498840332, "identity": 0.6536240577697754, "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_Concentration/a075e9fb61af20c8af787d11b0664db402ff882da57b93a650315898d01ed0da.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "a0ff56a0bc2f3d42f22f9015f444e80befa9dc8e55c0a12b9ed2c005f95071d3", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "e0828bc47292553fe006e6bde04e6554ec46186f80b061d030a80e111c4cc1bb", "generation_seconds_batch": 22.337733498075977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.000478744506836, "target_z": 1.8203125312317887, "ce": 6.062326908111572, "genuineness": 4.093128204345703, "identity": 0.8292886018753052, "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_Concentration/a0ff56a0bc2f3d42f22f9015f444e80befa9dc8e55c0a12b9ed2c005f95071d3.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "a14ea9738c1625d29be630d2c647a46e3d21e8b39e6d35b7b694acbbc0bb3323", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "1cd66fb7c5403f3202352de18841f160d90ef7aa833320dfa7c5402aaee9edbf", "generation_seconds_batch": 17.72492313804105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8235406875610352, "target_z": 1.5781249349868889, "ce": 6.0146708488464355, "genuineness": 4.337893962860107, "identity": 0.7089011669158936, "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_Concentration/a14ea9738c1625d29be630d2c647a46e3d21e8b39e6d35b7b694acbbc0bb3323.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "a26a514ef71018e7aa112646a6269b8e95552c45b4bb0d9e747761f15643da0b", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "3629ccb73e30331c878365487a70f797c908bef4c67e18631097aca7e16504a6", "generation_seconds_batch": 17.807628431008197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4810800552368164, "target_z": 1.1093749171401526, "ce": 6.403861999511719, "genuineness": 4.444586753845215, "identity": 0.37810632586479187, "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_Concentration/a26a514ef71018e7aa112646a6269b8e95552c45b4bb0d9e747761f15643da0b.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "a27700ad66988d936cbf5a049b93bed21bad4258a4fa1bf2b1367c9b41831d00", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9ef336e05b8150bdafb4685e21aad39fc3450d213f85e4f35977f416230abdac", "generation_seconds_batch": 16.675873777945526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9833557605743408, "target_z": 1.7968750956075163, "ce": 5.982900142669678, "genuineness": 4.6203155517578125, "identity": 0.4740086793899536, "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_Concentration/a27700ad66988d936cbf5a049b93bed21bad4258a4fa1bf2b1367c9b41831d00.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "a2fc69808747fe3387ee24e6d23ec2a13fe073b7ffa0ad627b6a7fd5f737a9ff", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "4a6fba928b3a2f6fb8af3dbd97dcdc16fd60c540475d0eed5d6bfc13def784f7", "generation_seconds_batch": 16.163968381937593, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3372316360473633, "target_z": 2.2812499617569935, "ce": 5.839932441711426, "genuineness": 4.306513786315918, "identity": 0.40509361028671265, "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_Concentration/a2fc69808747fe3387ee24e6d23ec2a13fe073b7ffa0ad627b6a7fd5f737a9ff.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "a3d9ee11b32cc65f0da16291f49cec05fbe38d4230cc42e11f4afc9d325ac1b2", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "e9ed4332d55bd8c8cb81efc3844395220b72963847ae5843f42f04432c8c2a63", "generation_seconds_batch": 23.962601884035394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9605250358581543, "target_z": 1.7656250726617124, "ce": 6.0146708488464355, "genuineness": 4.093128204345703, "identity": 0.4960743188858032, "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_Concentration/a3d9ee11b32cc65f0da16291f49cec05fbe38d4230cc42e11f4afc9d325ac1b2.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "a51246d10e55c95031979e0f27457bd2fd92a4750bffa9ecf79018077cdfc2ac", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "c0a55f7002354c64661b3cd950ceb14521f4aaca7108d35690e18444326509d3", "generation_seconds_batch": 23.96759530401323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9376943111419678, "target_z": 1.7343750497159085, "ce": 6.0305562019348145, "genuineness": 4.507347106933594, "identity": 0.766372799873352, "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_Concentration/a51246d10e55c95031979e0f27457bd2fd92a4750bffa9ecf79018077cdfc2ac.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "a512fc3a8c4ace2a1f103fe39170fb1590e32152ea3891f0853a057e9ebcb4f0", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d3158634de214c130c352ddde8ee66e4a7c596ec8a64552fbcb047fb74c92f13", "generation_seconds_batch": 24.0639628469944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9833557605743408, "target_z": 1.7968750956075163, "ce": 5.5539960861206055, "genuineness": 4.570107460021973, "identity": 0.6420577168464661, "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_Concentration/a512fc3a8c4ace2a1f103fe39170fb1590e32152ea3891f0853a057e9ebcb4f0.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "a537555e7ead7e2daf21502b840dedd2f8c07f1a778ee7f65c586408c73b8616", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "3de720a26e678578ec7ffe4b1cd0b384db2593d0a8995ec9887cd02a3df6458b", "generation_seconds_batch": 25.90532326803077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.732217788696289, "target_z": 1.4531248432036732, "ce": 5.258131504058838, "genuineness": 4.532451152801514, "identity": 0.5630109906196594, "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_Concentration/a537555e7ead7e2daf21502b840dedd2f8c07f1a778ee7f65c586408c73b8616.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "a5438d4fec6a2637bc520ff520a76cb8715320cf45b4f176bed0cc19eb9f5c7c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "5293a2b345b50dd23baeb5543055edfc6df989e5474679db2a6016e1c6bd89e2", "generation_seconds_batch": 23.465876513975672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8577868938446045, "target_z": 1.625000132575756, "ce": 5.40705680847168, "genuineness": 4.570107460021973, "identity": 0.6027663350105286, "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_Concentration/a5438d4fec6a2637bc520ff520a76cb8715320cf45b4f176bed0cc19eb9f5c7c.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "a5a08606e78f36e64a414e9ebf372f369f82727a039465b120b6a31e76c396c9", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "14f17105079b228a6b364291d59867009abb5386887a83e58340f1ba3a14a718", "generation_seconds_batch": 23.173379588057287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0975091457366943, "target_z": 1.9531248839962134, "ce": 5.879645347595215, "genuineness": 4.406930446624756, "identity": 0.5398138761520386, "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_Concentration/a5a08606e78f36e64a414e9ebf372f369f82727a039465b120b6a31e76c396c9.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "a5ce34250cc8e481b6ba2ab3b81345b834faec4676d948fef4f55fc21650483f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a5bcdfc38e53799b98bb54bc02e0bbdc58509cda35cf27068723866165e7bddf", "generation_seconds_batch": 22.021518954075873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5552799701690674, "target_z": 1.210937573299096, "ce": 6.046441555023193, "genuineness": 4.400654315948486, "identity": 0.575459361076355, "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_Concentration/a5ce34250cc8e481b6ba2ab3b81345b834faec4676d948fef4f55fc21650483f.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": "a5d16d338056c1917a4b9a78bb376eefeb4195e9b6fd4d8264d209897c7cfb59", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2bb1447329704b96559604dad2890617d782867c9a541765db51eb5fd1f0a8e3", "generation_seconds_batch": 16.784143800963648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.302985668182373, "target_z": 2.2343750905084487, "ce": 6.141753673553467, "genuineness": 4.65797233581543, "identity": 0.7754242420196533, "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_Concentration/a5d16d338056c1917a4b9a78bb376eefeb4195e9b6fd4d8264d209897c7cfb59.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "a5d525660bb410896467eed265ec0325506153aaa529561c04404761b2eb4725", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f3a45a0660ced3af7646e2a402293fe7c72bb449cadad337dead7ef1fa68f38f", "generation_seconds_batch": 24.017315658042207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8463714122772217, "target_z": 1.6093749579326928, "ce": 6.213237762451172, "genuineness": 4.017816066741943, "identity": 0.2424612045288086, "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_Concentration/a5d525660bb410896467eed265ec0325506153aaa529561c04404761b2eb4725.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "a5fd470f675c67bd1eb523e01362e9db9d5121a133e1b89f8ef03a570624cc78", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "dcd6f1b3ea2f12d7c38209af6b3c6a732a6c36aef3cc595c8769019044be2e21", "generation_seconds_batch": 22.299379269010387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.732217788696289, "target_z": 1.4531248432036732, "ce": 6.332377910614014, "genuineness": 4.293961524963379, "identity": 0.4957824945449829, "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_Concentration/a5fd470f675c67bd1eb523e01362e9db9d5121a133e1b89f8ef03a570624cc78.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": "a632fa902da11a152498935d7bcff1df584656357803455486fe7f4ab2e52e6c", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "854fc471a426ee69ee6cff846a79be956522edb4829343d7d9c9fd8540fb81a4", "generation_seconds_batch": 17.189596571028233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.971940279006958, "target_z": 1.7812499209644532, "ce": 6.252951145172119, "genuineness": 4.595211505889893, "identity": 0.7101485729217529, "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_Concentration/a632fa902da11a152498935d7bcff1df584656357803455486fe7f4ab2e52e6c.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "a65c8b3a7888de72169cb64c79cab11b41d0d478b9e0dce1c76dccde70f95168", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "8629bdc5fee887fa137ee3bd3b55e198514ea81102ace496627f28bd72615b89", "generation_seconds_batch": 23.493370078969747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1317553520202637, "target_z": 2.0000000815850805, "ce": 6.213237762451172, "genuineness": 4.457139015197754, "identity": 0.5663056969642639, "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_Concentration/a65c8b3a7888de72169cb64c79cab11b41d0d478b9e0dce1c76dccde70f95168.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "a67080579a5febccb025f894318a9d3184d945d0385abeb4b57cf1aba8821c48", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "32953c775a6b2f08333b9034de4ad964d1ac9a87cad24ab8a3e58c97e335d2ee", "generation_seconds_batch": 23.909070541965775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6066489219665527, "target_z": 1.2812498801719128, "ce": 6.062326908111572, "genuineness": 4.444586753845215, "identity": 0.6733809113502502, "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_Concentration/a67080579a5febccb025f894318a9d3184d945d0385abeb4b57cf1aba8821c48.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "a6e6984aa71abaa0390edd89e699670d3a8b22b64db006fb073b4c0a9c66e943", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "3944f7080c0c7e48eb05106232e8ed2976682519eb39bb9427db1622fe927cd7", "generation_seconds_batch": 23.437643697019666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4582493305206299, "target_z": 1.0781248941943486, "ce": 6.221180438995361, "genuineness": 4.193545341491699, "identity": 0.4946274757385254, "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_Concentration/a6e6984aa71abaa0390edd89e699670d3a8b22b64db006fb073b4c0a9c66e943.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "a6f288c5a6d3764c4c5be19256465e25a83c7ebed6d43ae2cdda325cd138de33", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "dd9f3952229d3f76fd0883b31b2a574f404de5484372236facd6076dc7d5d354", "generation_seconds_batch": 27.107375586987473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6066489219665527, "target_z": 1.2812498801719128, "ce": 6.284721851348877, "genuineness": 4.482243061065674, "identity": 0.36664265394210815, "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_Concentration/a6f288c5a6d3764c4c5be19256465e25a83c7ebed6d43ae2cdda325cd138de33.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "a70809bdb31b20ca8876d6e1bd8b82fa69fd89a0ecefdf9a52722cda681e5a7f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "9f8eaa37882cbe0f1a69cd5d5b384282eea3c3c6d8f25278b5f6e73c661f6e0f", "generation_seconds_batch": 23.787033897941, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2687394618988037, "target_z": 2.1874998929195817, "ce": 6.006728172302246, "genuineness": 4.331617832183838, "identity": 0.6136282682418823, "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_Concentration/a70809bdb31b20ca8876d6e1bd8b82fa69fd89a0ecefdf9a52722cda681e5a7f.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "a72a92d73369cf8fea6b5185e81fbba1515ff6db863e06849bc3a75efb9a18e9", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "d6a96a0b47a2ec87a3263c56bfb20eec2375e7e2adf92404ef72b77ceaa046e4", "generation_seconds_batch": 22.131983369006775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9890632629394531, "target_z": 1.8046873565887254, "ce": 6.133810997009277, "genuineness": 4.582659721374512, "identity": 0.8209709525108337, "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_Concentration/a72a92d73369cf8fea6b5185e81fbba1515ff6db863e06849bc3a75efb9a18e9.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "a787c9c745339ef09640e9c30485f736ef7d09dd6baec0eadc0bc94d9043e95b", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "a5046e95f0ecf4af3c3c25163b1afbab88307baa7a42120fece0dc0abcc50c06", "generation_seconds_batch": 23.265170424012467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3714778423309326, "target_z": 2.3281251593458605, "ce": 5.8875885009765625, "genuineness": 4.419482707977295, "identity": 0.6001443266868591, "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_Concentration/a787c9c745339ef09640e9c30485f736ef7d09dd6baec0eadc0bc94d9043e95b.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "a7f65cbce06105b9995a965c545a1d19d72698751f2d89628f1f038320bfeddb", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6084ab5a8801e04bf358f636167465000b72fd020449ca0e885108803fdcd41a", "generation_seconds_batch": 23.218509702011943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.384049654006958, "target_z": 0.9765625643757276, "ce": 5.879645347595215, "genuineness": 4.1998209953308105, "identity": 0.7105065584182739, "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_Concentration/a7f65cbce06105b9995a965c545a1d19d72698751f2d89628f1f038320bfeddb.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "a81c431f39bd327cf7e7f42e153c9eea5d8bc1996c6b576856e3eedf4df119f3", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "e183f2a1c18c24621d06eb222b9a24491acbc51628371c3cd5c0505e739b8ab5", "generation_seconds_batch": 23.82853389903903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7664639949798584, "target_z": 1.5000000407925402, "ce": 5.824047088623047, "genuineness": 4.068024158477783, "identity": 0.36220237612724304, "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_Concentration/a81c431f39bd327cf7e7f42e153c9eea5d8bc1996c6b576856e3eedf4df119f3.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "a845589f0e6959438e71a64dc79dbb6d7deeb2cf6dca08b2cffcef9ed32aaaca", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0363ba004833437aa5f68f01bb493729a3300683c1febe48a6d87c416d015a00", "generation_seconds_batch": 22.912916891044006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7493410110473633, "target_z": 1.476562605168268, "ce": 6.0305562019348145, "genuineness": 4.15588903427124, "identity": 0.2920772433280945, "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_Concentration/a845589f0e6959438e71a64dc79dbb6d7deeb2cf6dca08b2cffcef9ed32aaaca.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "a85951745d12f765d3524f7fdc46eddb2c2f981f3d1bc6b7b1ea3ac1fc9f8994", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "6ec7d580aa54f5e5a60e9a53b19fe15ac742a4d3a46cd6b7df1a3d57db43f9c7", "generation_seconds_batch": 23.457595338928513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5724029541015625, "target_z": 1.2343750089233683, "ce": 6.157639026641846, "genuineness": 4.306513786315918, "identity": 0.31042635440826416, "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_Concentration/a85951745d12f765d3524f7fdc46eddb2c2f981f3d1bc6b7b1ea3ac1fc9f8994.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "a892e92db6aa2313ffa7f845d92b1153f52ea501d2a657ce0a8768d7cd65d51c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "8967baa5255dc8bc7a4212400ee5fd6ae8aa644dabaa5e98132d1b046e1d8947", "generation_seconds_batch": 23.388731069047935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.15458607673645, "target_z": 2.0312501045308844, "ce": 5.982900142669678, "genuineness": 3.873466968536377, "identity": 0.62453293800354, "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_Concentration/a892e92db6aa2313ffa7f845d92b1153f52ea501d2a657ce0a8768d7cd65d51c.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "2c302dadc456315b4ef3aaee74387785b229dcbb640ee9d2e943cca5f469a8e1", "generation_seconds_batch": 18.437401100993156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5997848510742188, "target_z": 2.6406250624635774, "ce": 6.117925643920898, "genuineness": 4.545003414154053, "identity": 0.6395101547241211, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je 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_Concentration/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "a8f88ad4c4ed3d794910e638da881e0294bb089c016a8320f58f5b32b9a0ee7e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "3c107033946dd81210d06621200f4c924a9fe2def2da7c7ce8a3e73e78917987", "generation_seconds_batch": 21.248467418947257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2470653057098389, "target_z": 0.7890624267009041, "ce": 5.637393951416016, "genuineness": 4.413206577301025, "identity": 0.4998989403247833, "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_Concentration/a8f88ad4c4ed3d794910e638da881e0294bb089c016a8320f58f5b32b9a0ee7e.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": "a9332b92fb52718c6c92a7fa82daa4ccb939ea521d6791d368051947d8296516", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "97d32e028a399801abe6cd262a36251579a51aa69b2526572a75bdd1bec48106", "generation_seconds_batch": 23.02806291601155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.732217788696289, "target_z": 1.4531248432036732, "ce": 6.300607204437256, "genuineness": 4.507347106933594, "identity": 0.5679450631141663, "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_Concentration/a9332b92fb52718c6c92a7fa82daa4ccb939ea521d6791d368051947d8296516.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "cc153c9c4bf66480d3f7b3c46071a0544f55836455c0415f5b78a780389c49fd", "generation_seconds_batch": 18.23795158509165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8463714122772217, "target_z": 1.6093749579326928, "ce": 6.0146708488464355, "genuineness": 4.394378662109375, "identity": 0.796806812286377, "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_Concentration/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "a951d4254935a1166d39c2f59eaa9165c11e8f750a788b604071bf038209f380", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "5b8a356775d9e07786ac7d9288679010a39e771ecb2778919d0e75e757901709", "generation_seconds_batch": 23.68077501305379, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3926111459732056, "target_z": 0.9882812821878638, "ce": 6.062326908111572, "genuineness": 4.532451152801514, "identity": 0.8430271148681641, "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_Concentration/a951d4254935a1166d39c2f59eaa9165c11e8f750a788b604071bf038209f380.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": "a988ce24d6dea0b75197ddfcc1a943073839fc0ceb0721421151f7501a288cc0", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "eee5a6f2df7f7a3c140c40d5b9a53fd84516042c2651521507a38dfed098c4fe", "generation_seconds_batch": 15.67413882294204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9776480197906494, "target_z": 1.7890625082859848, "ce": 6.3641486167907715, "genuineness": 4.582659721374512, "identity": 0.21204552054405212, "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_Concentration/a988ce24d6dea0b75197ddfcc1a943073839fc0ceb0721421151f7501a288cc0.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "a9a42ff7e7343e990feb30608191b95dc92c358c25fbf4ac5f0c1b6fd94c3550", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "8e085b25bc785f729c13ba92e98459fec259670f3a4850ec5c142d068f1fa532", "generation_seconds_batch": 16.493485787068494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5724029541015625, "target_z": 1.2343750089233683, "ce": 6.141753673553467, "genuineness": 4.287685871124268, "identity": 0.36268988251686096, "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_Concentration/a9a42ff7e7343e990feb30608191b95dc92c358c25fbf4ac5f0c1b6fd94c3550.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "a9a5230ebbc7bbb6b2e733008440cab57e0e8cdb3bf476a7bce7767cf17efc76", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "f802dd1ff28f0ba3b021b75353442c04f9fa593ad7b58da87af99e4fc4fc1c07", "generation_seconds_batch": 23.06074238999281, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7493410110473633, "target_z": 1.476562605168268, "ce": 6.348263263702393, "genuineness": 4.545003414154053, "identity": 0.33028700947761536, "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_Concentration/a9a5230ebbc7bbb6b2e733008440cab57e0e8cdb3bf476a7bce7767cf17efc76.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "aa5c77adb77cfa35824bb5e1973ee8b40632c05aac00056a4033727d007dc562", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d324ab8068156842ef030129d2bc113badbcb5fb1f21fc94a8d651656146b989", "generation_seconds_batch": 24.19806946697645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.789294719696045, "target_z": 1.5312500637383442, "ce": 6.181467056274414, "genuineness": 4.457139015197754, "identity": 0.3325825035572052, "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_Concentration/aa5c77adb77cfa35824bb5e1973ee8b40632c05aac00056a4033727d007dc562.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "aa6722719ef4108e2bc701f35ce8a0f3ba45aaee2b4f0b638b980848382feb3c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "96811477458bf0e23748f7af319774a77acf5ab92d377d06055b26cf05c7cd6f", "generation_seconds_batch": 23.445701073040254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6865565776824951, "target_z": 1.3906251236523879, "ce": 6.157639026641846, "genuineness": 4.532451152801514, "identity": 0.26838719844818115, "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_Concentration/aa6722719ef4108e2bc701f35ce8a0f3ba45aaee2b4f0b638b980848382feb3c.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "aaa7ae798695daf1315cfedf121a0a5aa7a961527db7bf1a1cda5fa601c48de1", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "393c736c7ea5f81a7be9d3f833e7b607004fa17ea7e8352532c541331dbf0c63", "generation_seconds_batch": 22.968119185999967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.017601728439331, "target_z": 1.843749966856061, "ce": 6.324435234069824, "genuineness": 4.432034492492676, "identity": 0.5786828994750977, "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_Concentration/aaa7ae798695daf1315cfedf121a0a5aa7a961527db7bf1a1cda5fa601c48de1.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "aaa8a5a38a8f0909f29c37f0d2b346b481a258854b113dbd45bc8246b6d31ec0", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "1158b51b6e6f039e6f90326820ea15c88fb76de7a6c6127781d8718472a58040", "generation_seconds_batch": 23.324752028100193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.034724712371826, "target_z": 1.8671874024803332, "ce": 5.998785495758057, "genuineness": 4.557555198669434, "identity": 0.755925178527832, "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_Concentration/aaa8a5a38a8f0909f29c37f0d2b346b481a258854b113dbd45bc8246b6d31ec0.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "ab1ccacbdfe3de7f03bd96c20e3af2222e7dbb066038c0a205cdf657fbda532e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aba113b690de9085b656c52b31765343308d3804e9cbff197b379318f59b19e3", "generation_seconds_batch": 17.474895756924525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.971940279006958, "target_z": 1.7812499209644532, "ce": 5.692992687225342, "genuineness": 4.545003414154053, "identity": 0.6483017802238464, "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_Concentration/ab1ccacbdfe3de7f03bd96c20e3af2222e7dbb066038c0a205cdf657fbda532e.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "ab3690dd95e124a98732a356404cc6b210a0838f8f95b98cd7c14125085c4af6", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "aadb62635feee9404bd866b7b696f0ed88bf3904cece134cc2dfa063c076900e", "generation_seconds_batch": 23.743468948057853, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2915701866149902, "target_z": 2.2187499158653856, "ce": 6.109982967376709, "genuineness": 4.482243061065674, "identity": 0.4421907067298889, "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_Concentration/ab3690dd95e124a98732a356404cc6b210a0838f8f95b98cd7c14125085c4af6.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "3dc51188615aacc6c6035a6244b849c8c32145d64ade05fda01bbd424d755708", "generation_seconds_batch": 20.325696701998822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0233094692230225, "target_z": 1.8515625541775926, "ce": 6.459460258483887, "genuineness": 4.262581825256348, "identity": 0.5443318486213684, "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_Concentration/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "abc0bf3a30da8c6f06598cc212000e57546b3212a9499b35317c8911ca1e6ef0", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "ecae20c35dae38a6022aca89a52a1c913924bc945ee1fbe79c2c73ba48e4126d", "generation_seconds_batch": 22.1251248230692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.211662769317627, "target_z": 2.109374998725233, "ce": 5.903473377227783, "genuineness": 4.256305694580078, "identity": 0.5955349206924438, "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_Concentration/abc0bf3a30da8c6f06598cc212000e57546b3212a9499b35317c8911ca1e6ef0.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "abc2631e8c8b3b5a7e2006b23e044609ae66e2dd5d007b37eee2a2d3751bf4cb", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "fe82519cf32c3b3f58a291b93f525929e1c4947a649fc3f3a050bfb3bb675ded", "generation_seconds_batch": 23.49517510505393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7550485134124756, "target_z": 1.4843748661494771, "ce": 6.292664527893066, "genuineness": 4.18099308013916, "identity": 0.36083880066871643, "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_Concentration/abc2631e8c8b3b5a7e2006b23e044609ae66e2dd5d007b37eee2a2d3751bf4cb.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "abd3e0e61abd19cb6a09f82b809e909dc83ddd182f9125aca90483d1536353f3", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2e99d271569c89cbd14133f5b4a546aaebaac6c7fb268f5015950eacdb8708a7", "generation_seconds_batch": 22.885576279950328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.954817295074463, "target_z": 1.7578124853401809, "ce": 6.109982967376709, "genuineness": 4.042920112609863, "identity": 0.7024170160293579, "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_Concentration/abd3e0e61abd19cb6a09f82b809e909dc83ddd182f9125aca90483d1536353f3.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "acb85a9c6a6b68a5387502b92927043cc98bd24a7a7adeaaf260472f4c1d609c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "c449655c4efb2e9d6a6cb263f7f8baef2e5ee0000675f8e796a755eaecde8135", "generation_seconds_batch": 21.014710027026013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6808488368988037, "target_z": 1.3828125363308563, "ce": 6.181467056274414, "genuineness": 4.017816066741943, "identity": 0.31947827339172363, "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_Concentration/acb85a9c6a6b68a5387502b92927043cc98bd24a7a7adeaaf260472f4c1d609c.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "ad26a330b06856b49ccb6a62d5bd105a024671edea172d69fc94841bf369a911", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "6404c2a62ae3244f3452f39d51a489ea3bb369108091c3a7586f1bc215b37a4c", "generation_seconds_batch": 17.710494530037977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9890632629394531, "target_z": 1.8046873565887254, "ce": 6.308549880981445, "genuineness": 4.218649387359619, "identity": 0.5049014091491699, "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_Concentration/ad26a330b06856b49ccb6a62d5bd105a024671edea172d69fc94841bf369a911.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "ad2c80e50cd5c48a0300e2914761641aa88020d110d94fd755884d03bead5553", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "0115fa450618ee00f7120e2a29fc4ca57e6113e6d081526bab79aeb3c9cb204a", "generation_seconds_batch": 23.218509702011943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2344934940338135, "target_z": 2.140625021671037, "ce": 6.0146708488464355, "genuineness": 4.256305694580078, "identity": 0.4214705228805542, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen naar 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_Concentration/ad2c80e50cd5c48a0300e2914761641aa88020d110d94fd755884d03bead5553.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "ad33aae1078d1faef7551b12549d0b99344bce3e0ff7a81e24b8232dda9c3663", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "6f231426ad8b98b5ab04b7d39756b78a2737783b9961730f3949223d704ed148", "generation_seconds_batch": 15.719984838971868, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.25732421875, "target_z": 2.171875044616841, "ce": 5.692992687225342, "genuineness": 4.256305694580078, "identity": 0.6536719799041748, "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_Concentration/ad33aae1078d1faef7551b12549d0b99344bce3e0ff7a81e24b8232dda9c3663.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "ada128a981dfedb872b11cc1e609874293be670a6634276089ea60f392393459", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "8e39f45f7344276b58608938850aafd49472091babe722e91b803288fbeea940", "generation_seconds_batch": 24.09214202896692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7208025455474854, "target_z": 1.4374999949009324, "ce": 6.1894097328186035, "genuineness": 4.457139015197754, "identity": 0.5324912667274475, "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_Concentration/ada128a981dfedb872b11cc1e609874293be670a6634276089ea60f392393459.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "f2e4c40d7056d543870fe5c1f7996de6575b77a88862d18bf7525b36ee9949b1", "generation_seconds_batch": 17.149972542072646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.834956169128418, "target_z": 1.593750109629952, "ce": 6.078212261199951, "genuineness": 4.381826400756836, "identity": 0.6321618556976318, "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_Concentration/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "426519361892759738697fd40eee3bc1bf5899a48b234628c1990e652f902e15", "generation_seconds_batch": 18.060334723093547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.166001319885254, "target_z": 2.046874952833625, "ce": 6.467403411865234, "genuineness": 3.9299514293670654, "identity": 0.17752894759178162, "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_Concentration/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "af177981f51683cfe15738810c56bd6a4e5a88ac0faee1cf32f947628bc28238", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "77aa9e1634536918c69d3dafcac459e67754a0b889dee57bdedf57bb99fc8bc5", "generation_seconds_batch": 18.951957929995842, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8007099628448486, "target_z": 1.546874912041085, "ce": 5.49045467376709, "genuineness": 4.281409740447998, "identity": 0.7854952812194824, "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_Concentration/af177981f51683cfe15738810c56bd6a4e5a88ac0faee1cf32f947628bc28238.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": "afa06ebc88c429562dffaaccbaa9c4ee66b20044da4de22d9d0721bf4db4fdde", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8638c691f5a5915804ca9d203f414398de3332546e2d1f063fe45aabe69ed73d", "generation_seconds_batch": 15.030253333970904, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3714778423309326, "target_z": 2.3281251593458605, "ce": 5.784333229064941, "genuineness": 4.262581825256348, "identity": 0.7577744722366333, "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_Concentration/afa06ebc88c429562dffaaccbaa9c4ee66b20044da4de22d9d0721bf4db4fdde.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "afe07304386fd3b4ec643c90f160ed61e927d09956b087fa0c5538ed15d2927d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "9a70ba75b47ac78c3205609720962a418483b9325d995af09cfeb7498bc83bb2", "generation_seconds_batch": 22.020127641037107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.732217788696289, "target_z": 1.4531248432036732, "ce": 6.300607204437256, "genuineness": 4.532451152801514, "identity": 0.7239487767219543, "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_Concentration/afe07304386fd3b4ec643c90f160ed61e927d09956b087fa0c5538ed15d2927d.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "b0c595c8503348ac80a718d1064d0adad52b2ebb691e0829cf545cecbb7c0480", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "379db8402b252adb7676012762766d195919f652378a17227fb43c4fc6c2f388", "generation_seconds_batch": 22.83976077195257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6922640800476074, "target_z": 1.398437384633597, "ce": 6.308549880981445, "genuineness": 4.268857479095459, "identity": 0.4633404314517975, "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_Concentration/b0c595c8503348ac80a718d1064d0adad52b2ebb691e0829cf545cecbb7c0480.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "b0d4ea801fd07be777a4a0b1629dae430d54040a41c3c50101b29653f5e7c8dc", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "9ca4924d1c4d2842e3234c5808301a82ba3e2c92b4ff3220a013b5068df65d4f", "generation_seconds_batch": 21.02810282295104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9205713272094727, "target_z": 1.7109376140916361, "ce": 5.959072113037109, "genuineness": 4.607763767242432, "identity": 0.803328275680542, "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_Concentration/b0d4ea801fd07be777a4a0b1629dae430d54040a41c3c50101b29653f5e7c8dc.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "b1019a557d0d01fe6fd116dc974b3ad1dca30768bdf4a004f0a60f9195fe3aa1", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "10b13d28594407af84b00d5a8844e3a332d6a885f79342ef486bbcd7e4e435ec", "generation_seconds_batch": 15.984597087022848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9605250358581543, "target_z": 1.7656250726617124, "ce": 6.0305562019348145, "genuineness": 4.243753433227539, "identity": 0.6967741250991821, "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_Concentration/b1019a557d0d01fe6fd116dc974b3ad1dca30768bdf4a004f0a60f9195fe3aa1.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": "b10d61bdb77d032473edf0ceef9347c6def388e5a3c3f438116b55b7c79853d4", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "c2d5c5ac88bfc7378956c519dce77637d54713d0c92a3aa81a56b98fc3456b8e", "generation_seconds_batch": 17.734372997889295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7436332702636719, "target_z": 1.4687500178467363, "ce": 6.300607204437256, "genuineness": 4.381826400756836, "identity": 0.2645052969455719, "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_Concentration/b10d61bdb77d032473edf0ceef9347c6def388e5a3c3f438116b55b7c79853d4.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": "b13419de98e1294717cafacc7f438c06137c646869275206113658c2b6bf04fb", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "2a613f5982451a987fbf85ad80d52446a1a3e936bd042c0d58cc41776bf36e96", "generation_seconds_batch": 18.166690652025864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3144009113311768, "target_z": 2.2499999388111895, "ce": 6.173524379730225, "genuineness": 4.425758361816406, "identity": 0.20834694802761078, "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_Concentration/b13419de98e1294717cafacc7f438c06137c646869275206113658c2b6bf04fb.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": "b15275188b3ec431eefc8355ec831db6fa978366da1d4f8d16bc9023fbbce421", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c6d82d7d32f4c6afd6c4f5269ba55871ffff81d0a01e68905c7f9f796dbbba87", "generation_seconds_batch": 18.83027698006481, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3144009113311768, "target_z": 2.2499999388111895, "ce": 6.229123115539551, "genuineness": 4.024092197418213, "identity": 0.32268771529197693, "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_Concentration/b15275188b3ec431eefc8355ec831db6fa978366da1d4f8d16bc9023fbbce421.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "b1f496c4490b252f54bce55cd7c648b2021b140bf87150fd4a5ee47a2e0dece7", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "97b16cec44b2f234b325cdcaa94cfb0a0db53594e73e6519db96c41cd3a2a0fd", "generation_seconds_batch": 18.136188503005542, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9376943111419678, "target_z": 1.7343750497159085, "ce": 5.7684478759765625, "genuineness": 4.557555198669434, "identity": 0.829302966594696, "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_Concentration/b1f496c4490b252f54bce55cd7c648b2021b140bf87150fd4a5ee47a2e0dece7.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "b2bc16a92087c4cb478dd2f7579d70ca681ec9dae45532b9e813d5d0efc04b9c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "6307091c520b080264be816c598903f91ea0240784d1f5d28e2935e08677a69a", "generation_seconds_batch": 23.868621479021385, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0404324531555176, "target_z": 1.874999989801865, "ce": 5.982900142669678, "genuineness": 3.961331605911255, "identity": 0.649990439414978, "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_Concentration/b2bc16a92087c4cb478dd2f7579d70ca681ec9dae45532b9e813d5d0efc04b9c.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": "b3016ab9d592cc1da5881ce9ead9f451c2d33be65a4551cfea4922f5408f4dd9", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "55ca3a3afd4866d4d9c7901c000688a27b1df603220de02d0333c70ddfb44c31", "generation_seconds_batch": 22.0727027929388, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.348647117614746, "target_z": 2.2968751364000566, "ce": 6.046441555023193, "genuineness": 4.444586753845215, "identity": 0.6991103291511536, "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_Concentration/b3016ab9d592cc1da5881ce9ead9f451c2d33be65a4551cfea4922f5408f4dd9.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "b3b2769491f6a4b634ea0ffdc81c4a64abd6ca5f4f5511f556f93ac4b0d026b1", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "15ced57641582c8f68948d6162d150e818140c0f1f79d5d6f14a6ab49e7e2282", "generation_seconds_batch": 23.76125874405261, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9376943111419678, "target_z": 1.7343750497159085, "ce": 6.054384231567383, "genuineness": 4.406930446624756, "identity": 0.570525586605072, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können mensam 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_Concentration/b3b2769491f6a4b634ea0ffdc81c4a64abd6ca5f4f5511f556f93ac4b0d026b1.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "b3fc11b3957d9dd7bdb251a0a929c165ceaf8c24ae7655760a10975dbf51863d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "222f2b6bb35efdcb07f3ac324b1ddb166fc03ce2bff354c97d10ecebc296a3a7", "generation_seconds_batch": 23.000692607020028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5153262615203857, "target_z": 1.1562501147290196, "ce": 5.967014789581299, "genuineness": 4.400654315948486, "identity": 0.4344637989997864, "hypothesis": "I found the little box. It was beside the old window. We can look inside.", "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_Concentration/b3fc11b3957d9dd7bdb251a0a929c165ceaf8c24ae7655760a10975dbf51863d.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "b4178b45760245cd59abc1c9d4138d2e35bbbc683970ce1f64a193593c23226a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "92bc84287b70bfe05c0f1d8881b01696777b69fe1b73f0b5d73200bd10d4ef61", "generation_seconds_batch": 23.685162128997035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9833557605743408, "target_z": 1.7968750956075163, "ce": 6.221180438995361, "genuineness": 4.6203155517578125, "identity": 0.6504346132278442, "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_Concentration/b4178b45760245cd59abc1c9d4138d2e35bbbc683970ce1f64a193593c23226a.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "f7315d99446322dec033bb7644e452d17eef5f66487b61b6a7249afecd8cd11c", "generation_seconds_batch": 18.137304752948694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8749098777770996, "target_z": 1.6484375682000283, "ce": 6.260893821716309, "genuineness": 4.356721878051758, "identity": 0.735475480556488, "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_Concentration/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.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": "b5438f0d58ae5e1e45a4a98b64d620cd1276a158e49221e23db9a12d69513b7b", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "9a148a17116da73fe619e65f9298300958b90fe08486c5475e421449ecd6544e", "generation_seconds_batch": 14.825240619946271, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0404324531555176, "target_z": 1.874999989801865, "ce": 6.0305562019348145, "genuineness": 4.2249250411987305, "identity": 0.6214970350265503, "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana. Llévatelas cuando te vaya.", "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_Concentration/b5438f0d58ae5e1e45a4a98b64d620cd1276a158e49221e23db9a12d69513b7b.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "b5ec0ce7668c296f7805e0efccc683bb37f30d7eb501a87d5b202d35a08d71ad", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a54d013cab118d88e80b912a0d7aabdaea63eaa471ac1e5b754692208e8e9535", "generation_seconds_batch": 22.885576279950328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.166001319885254, "target_z": 2.046874952833625, "ce": 6.0305562019348145, "genuineness": 4.20609712600708, "identity": 0.7983740568161011, "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_Concentration/b5ec0ce7668c296f7805e0efccc683bb37f30d7eb501a87d5b202d35a08d71ad.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "b61d7233cf266fe1ffea7ac891f7af5619b82e765112699c1b6e1150c11ab415", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "cffb2ab07b3bce2a4f75189feb3792c8f1e542071d8355d8758b29e47666a1d5", "generation_seconds_batch": 22.020127641037107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9947710037231445, "target_z": 1.8124999439102571, "ce": 6.086154937744141, "genuineness": 4.268857479095459, "identity": 0.5265746712684631, "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_Concentration/b61d7233cf266fe1ffea7ac891f7af5619b82e765112699c1b6e1150c11ab415.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "b67248648f6ccbb2c4a065c75d8c0e8d799a818e2eda4e7bdab8f23e61cfc062", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc61ea41e5b24d9000b91e334ea07a98b498c18cbff0515d89897e4049004507", "generation_seconds_batch": 15.984597087022848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2915701866149902, "target_z": 2.2187499158653856, "ce": 5.839932441711426, "genuineness": 4.344170093536377, "identity": 0.5049186944961548, "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_Concentration/b67248648f6ccbb2c4a065c75d8c0e8d799a818e2eda4e7bdab8f23e61cfc062.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "b69d9f797d44844959ac511da74cfa3c212948999e7fc6010542e24760360ed3", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "7b2256714eef73d280575d5ec1c5f1f85feca41162eb68efcac08c01bb1c1b34", "generation_seconds_batch": 23.15741673100274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.503910779953003, "target_z": 1.1406249400859565, "ce": 5.824047088623047, "genuineness": 4.406930446624756, "identity": 0.8036450147628784, "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_Concentration/b69d9f797d44844959ac511da74cfa3c212948999e7fc6010542e24760360ed3.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": "b6c2857239b1cf9bf4191f70c0225bcedeb59a9a45f07274a05299236787fe3a", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "1cbee2ecb1ada641f2f71d478eaf1f0092da9e86dc529c74ded7a5428b81274a", "generation_seconds_batch": 14.825240619946271, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7265102863311768, "target_z": 1.4453125822224642, "ce": 6.09409761428833, "genuineness": 4.419482707977295, "identity": 0.695977509021759, "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana, llévatelas cuando te vaya.", "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_Concentration/b6c2857239b1cf9bf4191f70c0225bcedeb59a9a45f07274a05299236787fe3a.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "b6cb2227e11068cd1c4685ddc432a4e1af047e573715ed019d551d32139eb3cb", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "4afc512e7cf8c4425eb4071a765a879f228d6a1b91c302d1512bdd6bdad333f9", "generation_seconds_batch": 24.329404892981984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0860939025878906, "target_z": 1.9375000356934728, "ce": 5.967014789581299, "genuineness": 4.532451152801514, "identity": 0.7570748329162598, "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_Concentration/b6cb2227e11068cd1c4685ddc432a4e1af047e573715ed019d551d32139eb3cb.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": "b6e77d71bf670303c811364c5f720793c9ea8e31e2fb2836ee488fa5241fb7f4", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "3670c0afdc21c8128f2dff4a932e9c1157f3697f733ae97f9b7e3ae1664738d1", "generation_seconds_batch": 17.86147034005262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2344934940338135, "target_z": 2.140625021671037, "ce": 6.086154937744141, "genuineness": 4.432034492492676, "identity": 0.5451849699020386, "hypothesis": "Niemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na 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_Concentration/b6e77d71bf670303c811364c5f720793c9ea8e31e2fb2836ee488fa5241fb7f4.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "b82ea7916580353a2cdf93c7797edfc7cbe029feee30ad6c0a1131629f3802bd", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "abd17f66162da6be42c97de1de26ee63333be763528d3eed42b8858855e8a73e", "generation_seconds_batch": 23.481026871013455, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9890632629394531, "target_z": 1.8046873565887254, "ce": 5.95112943649292, "genuineness": 4.507347106933594, "identity": 0.713827908039093, "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_Concentration/b82ea7916580353a2cdf93c7797edfc7cbe029feee30ad6c0a1131629f3802bd.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "b840c48b2657e1730369dae1050ae04a070d1a0e0bdab8db5ca5056ed836c51d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "ea78d8f5afe5dea89adff10d1cc17d1caeab8ff02091aeac4c4fea604a7a3264", "generation_seconds_batch": 23.894188830046915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.074678421020508, "target_z": 1.9218748610504095, "ce": 6.332377910614014, "genuineness": 4.293961524963379, "identity": 0.6434766054153442, "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_Concentration/b840c48b2657e1730369dae1050ae04a070d1a0e0bdab8db5ca5056ed836c51d.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "b8a75f79211f691f04e571a80a1c28076b86a30c6e8ba77c05b0997ae08030d3", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9fb681a1125a9d9c3fea9ed1b4b4f8538370167d852ba3bdcf3c37d99a31e1c7", "generation_seconds_batch": 24.01979426795151, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9605250358581543, "target_z": 1.7656250726617124, "ce": 6.086154937744141, "genuineness": 4.557555198669434, "identity": 0.7497045397758484, "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_Concentration/b8a75f79211f691f04e571a80a1c28076b86a30c6e8ba77c05b0997ae08030d3.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "b8deb06776b13ede72adfac435da6c8b10b53fb99e848f4a7a05e37b822e782c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c85d005ccf12b27eb2fa30f82e7abe3eabef02c8120729ca95358f23ba7bd4f7", "generation_seconds_batch": 24.481677368981764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.166001319885254, "target_z": 2.046874952833625, "ce": 5.816103935241699, "genuineness": 4.3881025314331055, "identity": 0.6300304532051086, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre.", "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_Concentration/b8deb06776b13ede72adfac435da6c8b10b53fb99e848f4a7a05e37b822e782c.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "b931b6ed2a2c9e7a1ecf28b5d8b354bc3505b3128d2827404ddf630858e895db", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "1c83154d9daff0793ec180b0b0a5b2875b20b5fed76f39221f8e0084e51aa30d", "generation_seconds_batch": 24.653094066074118, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.029017210006714, "target_z": 1.8593751414991242, "ce": 5.546053409576416, "genuineness": 4.432034492492676, "identity": 0.8206809759140015, "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_Concentration/b931b6ed2a2c9e7a1ecf28b5d8b354bc3505b3128d2827404ddf630858e895db.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "b96177ecb6afeca040607ce4cda45a425ee40376543ea1032191cef3985383e1", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "9a11e331e577294f89b87d98d894da0e7c3ddffa75408cd62ab1636ce37f15fc", "generation_seconds_batch": 23.909070541965775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2801549434661865, "target_z": 2.203125067562645, "ce": 5.7406487464904785, "genuineness": 4.168440818786621, "identity": 0.6655839681625366, "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_Concentration/b96177ecb6afeca040607ce4cda45a425ee40376543ea1032191cef3985383e1.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "b9bbc9192fdf76d2c52e5c7d3704391a67fa7d0bb4019cf9e7907b763d098e4a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c59df4ed49db25e85c028a6ac389c57ef0168e137f3d591224c040ecacc1be19", "generation_seconds_batch": 23.53191199200228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0061864852905273, "target_z": 1.8281251185533203, "ce": 5.911416053771973, "genuineness": 4.507347106933594, "identity": 0.14971640706062317, "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_Concentration/b9bbc9192fdf76d2c52e5c7d3704391a67fa7d0bb4019cf9e7907b763d098e4a.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "ba251401572d42badfe44d2c07f0c6c84673a4f611adb23e51d117792d7ecf54", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "ab9693b086841a92c416f9e38e0634c016686082d74cf1699757d7be89feaf7d", "generation_seconds_batch": 24.08046322898008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.046140193939209, "target_z": 1.8828125771233966, "ce": 6.340320587158203, "genuineness": 4.2374773025512695, "identity": 0.5868196487426758, "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_Concentration/ba251401572d42badfe44d2c07f0c6c84673a4f611adb23e51d117792d7ecf54.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "ba33da5ca6aca199ac6bd922e088bf4cde2485bf79769521e10dfa852610bb2e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "6f06a69af5bb0ded883e45f74a46863421c5e6c6d13ff5bcd63fe64b04878214", "generation_seconds_batch": 18.168144646915607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.640895128250122, "target_z": 1.32812507776078, "ce": 6.229123115539551, "genuineness": 4.306513786315918, "identity": 0.6019831895828247, "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_Concentration/ba33da5ca6aca199ac6bd922e088bf4cde2485bf79769521e10dfa852610bb2e.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "6a098668561ace14c48c76fa3b4d3e7cc2353da75eea5e2d64a34fb5dd115dc2", "generation_seconds_batch": 17.816757199936546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.211662769317627, "target_z": 2.109374998725233, "ce": 6.197352409362793, "genuineness": 4.595211505889893, "identity": 0.6649966239929199, "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_Concentration/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "ba9465d9eea98e3a8957c05ecd9d0f533549ca008fa14848f9dfb28257e74880", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "c47e6aecf799f2ebf8615b90f16b15659cf39aaf727ea64eb118bfb0928f59a9", "generation_seconds_batch": 24.309824818978086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9890632629394531, "target_z": 1.8046873565887254, "ce": 6.23706579208374, "genuineness": 4.218649387359619, "identity": 0.5997819304466248, "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_Concentration/ba9465d9eea98e3a8957c05ecd9d0f533549ca008fa14848f9dfb28257e74880.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "baffea1c5430b4272051c9649d6a3a420cf7194e2c0bfb3611ecb37cfde4bc51", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "63ed9b59035964448347f74841e62cb891cd1521a2e5fc1058e6ba88837ddfed", "generation_seconds_batch": 16.675873777945526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.777879238128662, "target_z": 1.515624889095281, "ce": 6.205295085906982, "genuineness": 4.482243061065674, "identity": 0.696010947227478, "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_Concentration/baffea1c5430b4272051c9649d6a3a420cf7194e2c0bfb3611ecb37cfde4bc51.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "bb4152aa8968a46e5e03ce78431c7fe029fc185acc5f0d866f05022ebe22f7fa", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "055aae6575d10e96d5d22c069287ec67948347543ad53b0102f71fcead8cdb94", "generation_seconds_batch": 22.018248251988553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3258163928985596, "target_z": 2.2656251134542527, "ce": 6.038498878479004, "genuineness": 4.532451152801514, "identity": 0.534544050693512, "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_Concentration/bb4152aa8968a46e5e03ce78431c7fe029fc185acc5f0d866f05022ebe22f7fa.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": "bb5e3cf703e082370d3108d415d9dcf4b3a28a4726b7a894b790a412a0dc7c2f", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "da8c7cf8ad5651ce29c1249f788cf4549283f61c726cd34a936a01b6dff8273f", "generation_seconds_batch": 15.188658368075266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2185269594192505, "target_z": 0.7499999796037299, "ce": 6.300607204437256, "genuineness": 4.595211505889893, "identity": 0.7138041853904724, "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_Concentration/bb5e3cf703e082370d3108d415d9dcf4b3a28a4726b7a894b790a412a0dc7c2f.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "bb9c905e4e85dd74b3cccb15839c65d3fe74ae569961a9ab8ff614f8729235a5", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "bbd9196d119b6cb2f46547eaf78e00bbc3af2e91f4fb3732999f7bcf45483a59", "generation_seconds_batch": 23.493370078969747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9947710037231445, "target_z": 1.8124999439102571, "ce": 6.086154937744141, "genuineness": 4.319066047668457, "identity": 0.6407228708267212, "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_Concentration/bb9c905e4e85dd74b3cccb15839c65d3fe74ae569961a9ab8ff614f8729235a5.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": "bbd4c75de7bae75ab4766895c3899a4c45573b7e9bbc1b8fd3d1e979da40a9bf", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fe441efa5766c98e380eca1481d0edcdce7928dc2285550b4a5aecb32d5b1a0b", "generation_seconds_batch": 22.02929779002443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2915701866149902, "target_z": 2.2187499158653856, "ce": 6.403861999511719, "genuineness": 4.20609712600708, "identity": 0.19040489196777344, "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_Concentration/bbd4c75de7bae75ab4766895c3899a4c45573b7e9bbc1b8fd3d1e979da40a9bf.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "bc036d4172abddb488099adddd1780dc51e6058bcca9763166d0e02e4a2127b2", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "116251f3c37e41e4e5eca876315bccd7ca5bab878f64624b8c681ed044f4fc16", "generation_seconds_batch": 25.25904701196123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.017601728439331, "target_z": 1.843749966856061, "ce": 6.395919322967529, "genuineness": 4.281409740447998, "identity": 0.5366455316543579, "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_Concentration/bc036d4172abddb488099adddd1780dc51e6058bcca9763166d0e02e4a2127b2.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "bc08f1b2421e32a865f865ab8a1409d5657287bafefe6d43b705959bcdf580bc", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4cc171c2be187779298cdc00e97fddf28ad3bc34b6d70f82554b722b414b142f", "generation_seconds_batch": 17.82481366500724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6523103713989258, "target_z": 1.3437499260635206, "ce": 6.038498878479004, "genuineness": 4.507347106933594, "identity": 0.6353626251220703, "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_Concentration/bc08f1b2421e32a865f865ab8a1409d5657287bafefe6d43b705959bcdf580bc.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": "bcea7025dcd5bfe4aad52ee48ead31498643ccbe3d27eecca524b153fd47fdd4", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1a2e344a3ad0e63d30572b71c2c7b99d168ac9e1a88d215e5a82d3311d024189", "generation_seconds_batch": 23.69549362990074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6911075115203857, "target_z": 2.7656248279064704, "ce": 5.959072113037109, "genuineness": 4.356721878051758, "identity": 0.3176468014717102, "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_Concentration/bcea7025dcd5bfe4aad52ee48ead31498643ccbe3d27eecca524b153fd47fdd4.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "bd620d8b6e92b1a05679fbb2ad4155010bc46eca6222d8fc0cb5f8b22f7e22b3", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "223de32f4407eddc66c9a67d857203a2efc7bc3e6e254f417af82fe3a34b6b21", "generation_seconds_batch": 23.454739641980268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7835869789123535, "target_z": 1.5234374764168126, "ce": 6.117925643920898, "genuineness": 4.168440818786621, "identity": 0.2489190548658371, "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_Concentration/bd620d8b6e92b1a05679fbb2ad4155010bc46eca6222d8fc0cb5f8b22f7e22b3.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": "bd7922d3d6a8cafee698bd1c56d88e3fa287bd2535ffa81449b678ffffa1ecb0", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "92e28417867fcfedc86e9711dd4ab4648a432ed4bef55bac9bf58825d025d28c", "generation_seconds_batch": 17.49944514897652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6808488368988037, "target_z": 1.3828125363308563, "ce": 5.871703147888184, "genuineness": 4.557555198669434, "identity": 0.8732568025588989, "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_Concentration/bd7922d3d6a8cafee698bd1c56d88e3fa287bd2535ffa81449b678ffffa1ecb0.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "bdfff5cc6f764a347f2127d038ebc2e9693cda93a5232ba30548889db46ae7b4", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "f9201aeec3c4b5c8abb1fee589c258b654bad3c99aaf52394e2c81e828bd2df9", "generation_seconds_batch": 24.278018030920066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9491095542907715, "target_z": 1.7499998980186493, "ce": 6.022613525390625, "genuineness": 4.036643981933594, "identity": 0.716847836971283, "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_Concentration/bdfff5cc6f764a347f2127d038ebc2e9693cda93a5232ba30548889db46ae7b4.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "be2c21a51e8b5e82d2fd3f680778723ba068a12e04133a96211131dfd9d16930", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "98a5995ef08cdd98c524fcbabda2fdc417fc157ca7c50e19654f1490d34e14bd", "generation_seconds_batch": 15.067032163962722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9833557605743408, "target_z": 1.7968750956075163, "ce": 5.677107334136963, "genuineness": 4.444586753845215, "identity": 0.6102049946784973, "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_Concentration/be2c21a51e8b5e82d2fd3f680778723ba068a12e04133a96211131dfd9d16930.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "be5033a54dd5778464130a16339d6181a75085fb0f9b9df0cc8abb4ab9eed0cf", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d290f65f8d476c87806b911cd7b7a3518bb83d12da2992a59afad7620ec27f0e", "generation_seconds_batch": 24.03291548101697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4924955368041992, "target_z": 1.1250000917832157, "ce": 6.332377910614014, "genuineness": 4.381826400756836, "identity": 0.2249060869216919, "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_Concentration/be5033a54dd5778464130a16339d6181a75085fb0f9b9df0cc8abb4ab9eed0cf.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "be79272c44785f43237488fd709a02058d3fdcc78e5e4991a417376e512a1fa4", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "a0d74d7da9cae73a5ef8fe4501edb38686fa7f8c368892a797af2068df247ef4", "generation_seconds_batch": 24.050986264948733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9319865703582764, "target_z": 1.726562462394377, "ce": 6.499174118041992, "genuineness": 4.061748504638672, "identity": 0.553417980670929, "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_Concentration/be79272c44785f43237488fd709a02058d3fdcc78e5e4991a417376e512a1fa4.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": "be8056e392d8e7a980aa01b6b0fba45fa1a0bbf9d7af368841e78578257c1904", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "00d4ea10fcfa57202a8453108615852ed3470bb492b92c16ff049996458541e6", "generation_seconds_batch": 18.55700460402295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.166001319885254, "target_z": 2.046874952833625, "ce": 5.871703147888184, "genuineness": 4.7081804275512695, "identity": 0.7068607211112976, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/be8056e392d8e7a980aa01b6b0fba45fa1a0bbf9d7af368841e78578257c1904.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "bee4e7984acad7d99cc5f90b1681d754bdda99428a6c5d2c5f7e9de619bff9e9", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "79702d1fe5dd76cc965ea8cc777dfba3a3b732de3e73cda571ad725c9e141155", "generation_seconds_batch": 24.944193582050502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7036795616149902, "target_z": 1.4140625592766602, "ce": 6.157639026641846, "genuineness": 4.432034492492676, "identity": 0.523552417755127, "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_Concentration/bee4e7984acad7d99cc5f90b1681d754bdda99428a6c5d2c5f7e9de619bff9e9.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "bf36bcb10add839d966f62269487e9be73d2b27f57e2f52fd86e462ea28b0848", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a704861d235cce7eb32391cc652335c23e731df33732e0f24472ddaf319b4dcb", "generation_seconds_batch": 17.837136593065225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1260476112365723, "target_z": 1.992187494263549, "ce": 5.990842819213867, "genuineness": 4.068024158477783, "identity": 0.6202985644340515, "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_Concentration/bf36bcb10add839d966f62269487e9be73d2b27f57e2f52fd86e462ea28b0848.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "bf58a03ee535f39f7a95d50421a1d36362734821664c892b6d2183e53bd14a66", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "2b6ec04beb41986589fb614cd67e591b2602129cd2119cef34651759629bbbd1", "generation_seconds_batch": 22.33602329203859, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3726341724395752, "target_z": 0.9609373897326644, "ce": 5.085378646850586, "genuineness": 4.494794845581055, "identity": 0.6716669797897339, "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_Concentration/bf58a03ee535f39f7a95d50421a1d36362734821664c892b6d2183e53bd14a66.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "bfc669982fde783558bb1a025460a140a01f9574115e80959bd006ef5920151b", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "6f75ad44aad939053ed2f19108b8d6e63bf763be3bd606e9b27bd84ea5bceabb", "generation_seconds_batch": 23.858950015041046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6979718208312988, "target_z": 1.4062499719551285, "ce": 5.569881439208984, "genuineness": 4.218649387359619, "identity": 0.6985049247741699, "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_Concentration/bfc669982fde783558bb1a025460a140a01f9574115e80959bd006ef5920151b.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "bfdd0cd234d42193958c89761e5a65e98f7e96b6d62497d3d0ddd1006a89be3d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f496843fd8267d7a616435f1953e8176289d865f3d1411720a7327f8d4160fa0", "generation_seconds_batch": 22.117912009940483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.029017210006714, "target_z": 1.8593751414991242, "ce": 5.847874641418457, "genuineness": 4.432034492492676, "identity": 0.45437777042388916, "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_Concentration/bfdd0cd234d42193958c89761e5a65e98f7e96b6d62497d3d0ddd1006a89be3d.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "c28d33d9c5ed75f2bc4557be9eed88d648309e419f85c5b18f8727c00799bdb1", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "8d86c163f3fb3fea5e2587b8dae22072d0fb8d2e7ab16a110a1a1d9cfd18403f", "generation_seconds_batch": 21.712894549942575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6523103713989258, "target_z": 1.3437499260635206, "ce": 6.3641486167907715, "genuineness": 4.595211505889893, "identity": 0.26103493571281433, "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_Concentration/c28d33d9c5ed75f2bc4557be9eed88d648309e419f85c5b18f8727c00799bdb1.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "c2a71e5189c25f1b6232cefb74e00aab02cfd789348c052ce48b069e9e61f3f1", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "5a34cf922d266f73fb5ee84cad737021a3322853af73d3ef94a387ef71a27e6d", "generation_seconds_batch": 22.013855537050404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5096185207366943, "target_z": 1.148437527407488, "ce": 6.086154937744141, "genuineness": 4.444586753845215, "identity": 0.452072411775589, "hypothesis": "I found the little bock. 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_Concentration/c2a71e5189c25f1b6232cefb74e00aab02cfd789348c052ce48b069e9e61f3f1.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "c2d77c9ad9af11f9c70c9eb69b2f5cc121580350086767ef8c756e40c97dad8e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "887b7bbf310d8c99743111860113c7e911ee080f4a3ddf93dd8804cd5b648304", "generation_seconds_batch": 23.0887709580129, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1431705951690674, "target_z": 2.0156249298878213, "ce": 5.871703147888184, "genuineness": 4.532451152801514, "identity": 0.7066525220870972, "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_Concentration/c2d77c9ad9af11f9c70c9eb69b2f5cc121580350086767ef8c756e40c97dad8e.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "c2e978ad3d03d6382585adb6921f0dcc09aadc7f28741dd723b0d7c4a2cd0e03", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "ab006a817f4ef6d7824dc7419dc771063495d93e213a4c9116eef8e8e6f8f28e", "generation_seconds_batch": 21.60325988009572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2002475261688232, "target_z": 2.0937501504224922, "ce": 6.062326908111572, "genuineness": 4.356721878051758, "identity": 0.6772758364677429, "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_Concentration/c2e978ad3d03d6382585adb6921f0dcc09aadc7f28741dd723b0d7c4a2cd0e03.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "c3304b9ed3f500e4bb703e7931298defba416dc8d4c61b66229e94c8c030d5af", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "d88cd4c98a3990288fea182713b30cc826f3672a68b2a0d7ebfbd91e4a8e7f21", "generation_seconds_batch": 18.0502514350228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.405723810195923, "target_z": 2.3750000305944052, "ce": 6.173524379730225, "genuineness": 4.413206577301025, "identity": 0.5367715358734131, "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_Concentration/c3304b9ed3f500e4bb703e7931298defba416dc8d4c61b66229e94c8c030d5af.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "342c47cee494e93beaeb44c2603591506a965f8ea15340e13f5e8d395eb30ee2", "generation_seconds_batch": 18.12405549606774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0061864852905273, "target_z": 1.8281251185533203, "ce": 6.157639026641846, "genuineness": 4.607763767242432, "identity": 0.6701040267944336, "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_Concentration/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "c4061baf5e78734a78db7b19d9f3424457ec5b64d82054ee3af2d0192096ed5e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "94845cf93179980280def37cfae656385f04fb9bebf081dec3be331bc67cb156", "generation_seconds_batch": 24.874171786941588, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9662327766418457, "target_z": 1.773437659983244, "ce": 6.133810997009277, "genuineness": 4.444586753845215, "identity": 0.5327465534210205, "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_Concentration/c4061baf5e78734a78db7b19d9f3424457ec5b64d82054ee3af2d0192096ed5e.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "435e50bdfb4f8b46817d78be8cdd53bfc9ffe8232d8f0ea2bf385abd8098bd08", "generation_seconds_batch": 18.28961330105085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.017601728439331, "target_z": 1.843749966856061, "ce": 6.284721851348877, "genuineness": 4.344170093536377, "identity": 0.7994645833969116, "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_Concentration/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "c4e81b57996017864423edda822245363f96c806d3007be2a85a48fd09d6e56f", "bucket": "emo_Concentration", "phase": "wording", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "abc396c619cda0af6c447a1eddd5b754636a7a3fac95a9687b4026bc3258623c", "generation_seconds_batch": 16.47890271199867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3612189292907715, "target_z": 0.9453125414299237, "ce": 6.316492557525635, "genuineness": 4.582659721374512, "identity": 0.514711856842041, "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_Concentration/c4e81b57996017864423edda822245363f96c806d3007be2a85a48fd09d6e56f.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "c521e32225044fdae9f07b1d436f5f9719f5e85e6f00d856f6f2c2578568afed", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "daae7fa02dc3151cbeb6a08b79d14d2f06e354c149cd9d6247232696d44137c6", "generation_seconds_batch": 24.717872282955796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.715094804763794, "target_z": 1.4296874075794008, "ce": 6.197352409362793, "genuineness": 4.268857479095459, "identity": 0.186408132314682, "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_Concentration/c521e32225044fdae9f07b1d436f5f9719f5e85e6f00d856f6f2c2578568afed.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": "c599b41d498b0f60924c04e717bd5ebcddb6b9b270dc250c4aa14e209eaef34c", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f9ac15f28334bdbcbcca3b8220f57d537350e01d8ba71fed0a95c59280888566", "generation_seconds_batch": 18.83027698006481, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2002475261688232, "target_z": 2.0937501504224922, "ce": 6.348263263702393, "genuineness": 4.2374773025512695, "identity": 0.4454672038555145, "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_Concentration/c599b41d498b0f60924c04e717bd5ebcddb6b9b270dc250c4aa14e209eaef34c.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "c64b2df161abd3377e4eca65bf2614544d0ed36b32a4e5b1ce98fa32f0c1f3dc", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "029b5ad1da042cab580a176fd0518f90878366e5a9f0b15555c31de42ff737d7", "generation_seconds_batch": 23.869160891044885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7208025455474854, "target_z": 1.4374999949009324, "ce": 6.157639026641846, "genuineness": 4.494794845581055, "identity": 0.6631264686584473, "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_Concentration/c64b2df161abd3377e4eca65bf2614544d0ed36b32a4e5b1ce98fa32f0c1f3dc.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "c69834bf0412a72e2eedfa40ca4bed54679411f7f1d9d8cdcd8fb524e11a3838", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "57e8831476366bcdd08d1c678c859ff7afb9b3e69780a17935dbe1dcfe403a47", "generation_seconds_batch": 23.889214066090062, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1260476112365723, "target_z": 1.992187494263549, "ce": 5.824047088623047, "genuineness": 4.231201171875, "identity": 0.6038739085197449, "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_Concentration/c69834bf0412a72e2eedfa40ca4bed54679411f7f1d9d8cdcd8fb524e11a3838.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "c6d229feeaa84fd23b425bc948b1129a25095ebd5d43843603e8f0d06c984ce1", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "905fb7d33afbb86cd43b7aba03c8865eb84b63e37200102e7d507f09c0254633", "generation_seconds_batch": 23.66202667192556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8692021369934082, "target_z": 1.6406249808784967, "ce": 6.078212261199951, "genuineness": 4.7332844734191895, "identity": 0.7410646677017212, "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_Concentration/c6d229feeaa84fd23b425bc948b1129a25095ebd5d43843603e8f0d06c984ce1.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "c711a2ea7ed449333258820f468f89626fbb603ed31aa1abe7726b0c9609e055", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "52b8ea8af1d1c0fc0dbe8186b88806da70493db5d29401a26ee60fcdfefafee9", "generation_seconds_batch": 24.78633777203504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6637258529663086, "target_z": 1.359375100706584, "ce": 6.300607204437256, "genuineness": 4.645420074462891, "identity": 0.6503872871398926, "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_Concentration/c711a2ea7ed449333258820f468f89626fbb603ed31aa1abe7726b0c9609e055.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "c739b8ca7f7e2d914be784e9d7ac2b4a742206768745da3c59658dc90fa8201b", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "fbd98abc7e845b25bce14d063093d976810299c233dc79d0dbbb03c33c85d53e", "generation_seconds_batch": 22.655093441018835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0860939025878906, "target_z": 1.9375000356934728, "ce": 5.784333229064941, "genuineness": 4.118232727050781, "identity": 0.6447747945785522, "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_Concentration/c739b8ca7f7e2d914be784e9d7ac2b4a742206768745da3c59658dc90fa8201b.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "f78d73c5318f73d88f6b42712d6efb8771a739d31d0880af3ae46f665070f3d4", "generation_seconds_batch": 17.149972542072646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.971940279006958, "target_z": 1.7812499209644532, "ce": 6.054384231567383, "genuineness": 4.375550270080566, "identity": 0.6735897660255432, "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_Concentration/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "c83e1b096db7da796ceb6c132cad38a1dff8600253103df782f5c84a0e5d2941", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "b1146c9f5c5533ef7e75576c00d64b48c94d7d764175bc3a8ec8681bad98b71b", "generation_seconds_batch": 17.474895756924525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8178329467773438, "target_z": 1.5703123476653573, "ce": 5.593709468841553, "genuineness": 4.319066047668457, "identity": 0.5945266485214233, "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_Concentration/c83e1b096db7da796ceb6c132cad38a1dff8600253103df782f5c84a0e5d2941.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "c889a985510a183d3f4cab3bf0bd0b8679bfdd5722d64d016e430b363d87cb49", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "f0b6052de609050a8c83c8df59f789103cc239e1e85598b9664f1be34ea88193", "generation_seconds_batch": 21.92331942601595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.046140193939209, "target_z": 1.8828125771233966, "ce": 6.205295085906982, "genuineness": 4.18099308013916, "identity": 0.7349979877471924, "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_Concentration/c889a985510a183d3f4cab3bf0bd0b8679bfdd5722d64d016e430b363d87cb49.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "84ebb711baff98cd921e9505cbee3fed03161f5e755bda433e8cfb36f69bb1d8", "generation_seconds_batch": 18.29220380098559, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8692021369934082, "target_z": 1.6406249808784967, "ce": 6.300607204437256, "genuineness": 4.344170093536377, "identity": 0.2615496516227722, "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_Concentration/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.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": "c89c74a4b24a913ed134772286e7ba265088547be71bc4638a82c2d28a720797", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "f4b3e7e3f1bdfa62f5717af330be6efc0a70d6fb21eb9bb1e57ad7270188f38c", "generation_seconds_batch": 17.86147034005262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3144009113311768, "target_z": 2.2499999388111895, "ce": 6.125868320465088, "genuineness": 4.532451152801514, "identity": 0.5204281806945801, "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_Concentration/c89c74a4b24a913ed134772286e7ba265088547be71bc4638a82c2d28a720797.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "c8b01f446e0bd228a7905a4fbbff2e3a7138a8b5dfc1d1f81a7b438a6f0b29c5", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "897029ea272a31f92666f1395b2fb0d9d4d43baba72a7ebd26453bdacf82f037", "generation_seconds_batch": 25.464599517988972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.595233678817749, "target_z": 1.2656250318691722, "ce": 5.522225379943848, "genuineness": 4.494794845581055, "identity": 0.6623989343643188, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás libre.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/c8b01f446e0bd228a7905a4fbbff2e3a7138a8b5dfc1d1f81a7b438a6f0b29c5.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": "c9a728d30643bd9f6c377af6fbf1fa9e2f26f75a0d990efbd3e7c88cba6b0837", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e281e990a4eb78d7ac9e3fc37a329a36818b0513d2d0f3f3d0a91b907f261c68", "generation_seconds_batch": 18.32915610296186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9491095542907715, "target_z": 1.7499998980186493, "ce": 6.157639026641846, "genuineness": 4.469690799713135, "identity": 0.8081578016281128, "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_Concentration/c9a728d30643bd9f6c377af6fbf1fa9e2f26f75a0d990efbd3e7c88cba6b0837.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": "ca6313d246b3f6e11f0df5d486d5d541aefbffce56520e785b7d955a7fb74c3e", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "98dd6ee14f4c51267ddff7922c4038f77373ae86e6e80468a84109fa7f8f9308", "generation_seconds_batch": 17.734372997889295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.074678421020508, "target_z": 1.9218748610504095, "ce": 6.332377910614014, "genuineness": 4.325342178344727, "identity": 0.18537569046020508, "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_Concentration/ca6313d246b3f6e11f0df5d486d5d541aefbffce56520e785b7d955a7fb74c3e.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "cb1d3e30d5b9c7ad5ce24aa289e12058a5ed2dca0e229d38ea59c7afc0406b2c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d0402655c1c96ac94eeb3084b0579daa0b4306ccd5705512d1c6fd2e8638d670", "generation_seconds_batch": 23.96759530401323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9491095542907715, "target_z": 1.7499998980186493, "ce": 6.1894097328186035, "genuineness": 4.833701133728027, "identity": 0.7795353531837463, "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_Concentration/cb1d3e30d5b9c7ad5ce24aa289e12058a5ed2dca0e229d38ea59c7afc0406b2c.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "cb40e4b644045dabc5549b8c96a12446e37c5096cbb70208c0414700ec982e41", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "df127070c8d3710685904a64b286f8edd854d22c833f4b2f8078ece039bccdc9", "generation_seconds_batch": 23.580855860025622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.954817295074463, "target_z": 1.7578124853401809, "ce": 6.117925643920898, "genuineness": 4.519899368286133, "identity": 0.3973281681537628, "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_Concentration/cb40e4b644045dabc5549b8c96a12446e37c5096cbb70208c0414700ec982e41.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "cb6b34163136707a2795642a3532abc1f08673cc27ee403a0d79986d226c4ba2", "bucket": "emo_Concentration", "phase": "wording", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "e6d40650d5a67e9b2f3e9303f9b40b7dafa5f70716e8591cb928f6cf57f101d6", "generation_seconds_batch": 16.404450666042976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2002475261688232, "target_z": 2.0937501504224922, "ce": 6.006728172302246, "genuineness": 4.20609712600708, "identity": 0.4454612135887146, "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_Concentration/cb6b34163136707a2795642a3532abc1f08673cc27ee403a0d79986d226c4ba2.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "cb8357e940825369ecfe75f430349094147d7a29e9fcf6c9a842b304b31cf627", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "06967ad9147c208a45555076a9f7eb5bda8ac94acad53e4bb5173c1fc1190cff", "generation_seconds_batch": 18.12193335709162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5267415046691895, "target_z": 1.1718749630317604, "ce": 6.046441555023193, "genuineness": 4.2374773025512695, "identity": 0.42620521783828735, "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_Concentration/cb8357e940825369ecfe75f430349094147d7a29e9fcf6c9a842b304b31cf627.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "cc191d434943e2f1e27471c98386595422d4197ddbf6243ed77b7bbbc529f980", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "3b796d319dc4a9ee2d586e5391801de079fda70db53bd6cbd2398a122b10e0ab", "generation_seconds_batch": 25.056017081951723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9947710037231445, "target_z": 1.8124999439102571, "ce": 5.879645347595215, "genuineness": 4.381826400756836, "identity": 0.5474711060523987, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/cc191d434943e2f1e27471c98386595422d4197ddbf6243ed77b7bbbc529f980.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": "cc5cdd2b86bb7337d6d408826ec85340f2227ad32b7a4c418b94d4a4a08ba9b8", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "594769ab3e3a58b89afcbd153e6cc7564f7864c9c586b115ca480c55324c6e8c", "generation_seconds_batch": 17.11697677394841, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.384049654006958, "target_z": 0.9765625643757276, "ce": 5.538110733032227, "genuineness": 4.582659721374512, "identity": 0.7668955326080322, "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_Concentration/cc5cdd2b86bb7337d6d408826ec85340f2227ad32b7a4c418b94d4a4a08ba9b8.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "ccb3b9e33b3eb09f70d7509a8c47e06521d5c1471dfa3eb35a1c2ff7a1247c2c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "21af3296505e167f1383579ee302bf2d378fe6430d55dcb0eb427ce29a4b26a7", "generation_seconds_batch": 18.099706332897767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9605250358581543, "target_z": 1.7656250726617124, "ce": 5.585766792297363, "genuineness": 4.595211505889893, "identity": 0.47183358669281006, "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_Concentration/ccb3b9e33b3eb09f70d7509a8c47e06521d5c1471dfa3eb35a1c2ff7a1247c2c.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "ccba02d005ef898be43d895dc173ead7faa3c47e36e9ef028acded7e7e49c782", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4742ed2f1f2471e9c905c4396b7a94fbcb31aa768dd9e29f7997293e83c1141", "generation_seconds_batch": 23.784400914097205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0404324531555176, "target_z": 1.874999989801865, "ce": 5.550024509429932, "genuineness": 4.419482707977295, "identity": 0.5027028918266296, "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_Concentration/ccba02d005ef898be43d895dc173ead7faa3c47e36e9ef028acded7e7e49c782.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "cd7783859063be7e3e5f628fd47177e0bc7a4f5bd8b545e4ca802c1d72e9be75", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "ee92d2d4c3d2a7037d9a65d20bb9739fe29b615e760604d57da27453092c053f", "generation_seconds_batch": 27.107375586987473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5724029541015625, "target_z": 1.2343750089233683, "ce": 5.9431867599487305, "genuineness": 4.268857479095459, "identity": 0.3486347794532776, "hypothesis": "I found the little box. It was beside the old window. We can look inside to", "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_Concentration/cd7783859063be7e3e5f628fd47177e0bc7a4f5bd8b545e4ca802c1d72e9be75.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "cd7f1a7330e763b88ca6040b07c0567e523494f887b856aea8ba639bc05ea4b6", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "54b97e212cacf7c387a15d62786b542c060d18c6501e927604668c79909f8a80", "generation_seconds_batch": 24.232988427043892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5267415046691895, "target_z": 1.1718749630317604, "ce": 6.332377910614014, "genuineness": 4.582659721374512, "identity": 0.4888114333152771, "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_Concentration/cd7f1a7330e763b88ca6040b07c0567e523494f887b856aea8ba639bc05ea4b6.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "cd939082c69b80654a0f995e3924f907ff2f760902d5c84714949c203087cd6e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "19de56b1d59525e5a0bb7ae0a25ed1bd0221034ca77af4038272fe7a3b9675b0", "generation_seconds_batch": 23.82982732995879, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9833557605743408, "target_z": 1.7968750956075163, "ce": 5.808161735534668, "genuineness": 4.545003414154053, "identity": 0.7404366731643677, "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_Concentration/cd939082c69b80654a0f995e3924f907ff2f760902d5c84714949c203087cd6e.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "cdeaa55f156d2a82a72a550e9b92f4b60cc5eee87d48bb7f5d65743f746afdc4", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "897adfa7807f603efe868398e9fa3c0a01b66cce6822e612f7af24d6b5e2b843", "generation_seconds_batch": 22.931006058002822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.211662769317627, "target_z": 2.109374998725233, "ce": 6.062326908111572, "genuineness": 4.557555198669434, "identity": 0.5162016153335571, "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_Concentration/cdeaa55f156d2a82a72a550e9b92f4b60cc5eee87d48bb7f5d65743f746afdc4.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "cdff2cad0155bebaa5668ff1028d003e278b23363ddfda462388a63df3584d83", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "53d937ce2b66297ada668f3e026d0571dd09d2c4dafb0c968ed4f2087cf7ad03", "generation_seconds_batch": 19.2257806439884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2128193378448486, "target_z": 0.7421875554523595, "ce": 6.435632705688477, "genuineness": 4.394378662109375, "identity": 0.45186102390289307, "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_Concentration/cdff2cad0155bebaa5668ff1028d003e278b23363ddfda462388a63df3584d83.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "ce1b19527f2b6d6992f47d05723e769776ddd8c8e7eabc4b661de0aadfcd15f7", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "84337a37e53d07beda1292742843863480cc015f4c67fbaaf74e801d5814d02e", "generation_seconds_batch": 23.53191199200228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7379255294799805, "target_z": 1.4609374305252047, "ce": 5.982900142669678, "genuineness": 4.607763767242432, "identity": 0.6716374158859253, "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_Concentration/ce1b19527f2b6d6992f47d05723e769776ddd8c8e7eabc4b661de0aadfcd15f7.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "ce3f3123c5c2d72a6ddcd48c21f80c49a46c77b69748b613abd0565567dae841", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "431fb5f7a4e5f2ecbd5b26677cb10bf13c94fbe7dbef46271b658759517bf69f", "generation_seconds_batch": 17.252879387000576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9491095542907715, "target_z": 1.7499998980186493, "ce": 5.478540420532227, "genuineness": 4.632867813110352, "identity": 0.7878986597061157, "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_Concentration/ce3f3123c5c2d72a6ddcd48c21f80c49a46c77b69748b613abd0565567dae841.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "ce540cab767da322826746c09ab906717ab073322daf797137bf790296dbd1a2", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "a53d8889e86233cd1b67604e156304d49ed3a456f0753f20f40e46b4741a6d61", "generation_seconds_batch": 24.01979426795151, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.880617618560791, "target_z": 1.6562501555215599, "ce": 6.229123115539551, "genuineness": 4.883909225463867, "identity": 0.8840284943580627, "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_Concentration/ce540cab767da322826746c09ab906717ab073322daf797137bf790296dbd1a2.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": "cea5c2b7575deb75c1da9127df4890e70c30cbb520c0ff91ab794cef00e031ca", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dba5d1bf66bdb4f1faec79a4990b2b7ecbebbe821d840400b217061e0e4de67b", "generation_seconds_batch": 18.174507802003063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.732217788696289, "target_z": 1.4531248432036732, "ce": 6.221180438995361, "genuineness": 4.7081804275512695, "identity": 0.633073091506958, "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_Concentration/cea5c2b7575deb75c1da9127df4890e70c30cbb520c0ff91ab794cef00e031ca.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": "cee7a599a9d0fae07fe2175f4ea185a65bd5869a9b22b80705f9cbecc9132e40", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "77e802d24eef70a32c694c32c65189f21ec0f22741a28886db93fc5ba01f7bfc", "generation_seconds_batch": 16.77695035992656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6682770252227783, "target_z": 2.734375131300989, "ce": 6.046441555023193, "genuineness": 4.381826400756836, "identity": 0.6533269882202148, "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_Concentration/cee7a599a9d0fae07fe2175f4ea185a65bd5869a9b22b80705f9cbecc9132e40.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": "cef0005937d28ae9986ad50f0ca18b5ab8b75c7f51ae5462c0deead83cdadadc", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2ae5f0d4ddbb367ec5dbd55406a5eba09da99ff972d79aa2befbdf9d948a9c89", "generation_seconds_batch": 23.984171253978275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.211662769317627, "target_z": 2.109374998725233, "ce": 6.467403411865234, "genuineness": 4.325342178344727, "identity": 0.22142919898033142, "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_Concentration/cef0005937d28ae9986ad50f0ca18b5ab8b75c7f51ae5462c0deead83cdadadc.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "cf1c0f6be745bbc40a0710819cbcc389de802aac159bd3e835e41ab55a7edd37", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "fab1b450e54394c1de79abdbcca3d3049afc93751fc61f77a64de8e028ddddfa", "generation_seconds_batch": 24.065952492994256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9205713272094727, "target_z": 1.7109376140916361, "ce": 6.022613525390625, "genuineness": 3.8044304847717285, "identity": 0.5831149816513062, "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_Concentration/cf1c0f6be745bbc40a0710819cbcc389de802aac159bd3e835e41ab55a7edd37.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "18f20f675a3e431951ab7e6a8848f5b4e11f37f1c70bce01a709902ce36aba02", "generation_seconds_batch": 17.642865570960566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.000478744506836, "target_z": 1.8203125312317887, "ce": 6.41180419921875, "genuineness": 4.532451152801514, "identity": 0.5983375310897827, "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_Concentration/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "cfb2edb8e08ec056945cc8a842d8147d6b65954e642c644117f6899a20a31b05", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e8d9007797a2f23876567d09dfb2b1a5a579b4069577bf7c8cfe040be1125a87", "generation_seconds_batch": 26.163879495928995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2230780124664307, "target_z": 2.124999847027974, "ce": 6.038498878479004, "genuineness": 4.2751336097717285, "identity": 0.6965477466583252, "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_Concentration/cfb2edb8e08ec056945cc8a842d8147d6b65954e642c644117f6899a20a31b05.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "d08bc1765a71e7981e2de74a45749d677bda43edce511e01059370af404b2216", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "ab5497b1012e461e0e12380a6f7da5540ebb38c655b69ee7ddb135e7ba63c06a", "generation_seconds_batch": 23.06074238999281, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6979718208312988, "target_z": 1.4062499719551285, "ce": 6.24500846862793, "genuineness": 4.325342178344727, "identity": 0.4737613797187805, "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_Concentration/d08bc1765a71e7981e2de74a45749d677bda43edce511e01059370af404b2216.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "e65cda6a4b130b5ec9a8530a70aa5d5ec042a6dcd182612e19fcf8b020089bdb", "generation_seconds_batch": 16.360429111053236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.245908737182617, "target_z": 2.1562498699737778, "ce": 6.348263263702393, "genuineness": 3.911123275756836, "identity": 0.42642921209335327, "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_Concentration/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "d128e4c921f67e7f5568e3b96b0b8a1f9f92555df6263c466f4520a26885fb95", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "261aef4992a977ed8baa505ea74c48a5c4e4d2990002bf420a35c97c4bbd2cc8", "generation_seconds_batch": 16.163968381937593, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1032168865203857, "target_z": 1.960937471317745, "ce": 5.959072113037109, "genuineness": 4.256305694580078, "identity": 0.24596178531646729, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude ram. 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_Concentration/d128e4c921f67e7f5568e3b96b0b8a1f9f92555df6263c466f4520a26885fb95.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "d13c7e3b914618ad73721239d01c6fa2e3e7f226b6626f4e8a7f3540af0ec3e2", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0b7f469ce591d4bd744b49990e6a0fcdc9e7dc4d3fbe4a4f58f1e8adcc54d68b", "generation_seconds_batch": 24.426575263030827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8178329467773438, "target_z": 1.5703123476653573, "ce": 5.919358730316162, "genuineness": 4.645420074462891, "identity": 0.6879531741142273, "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_Concentration/d13c7e3b914618ad73721239d01c6fa2e3e7f226b6626f4e8a7f3540af0ec3e2.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "d18d34450b409ed5d56b861e8b6734dbc7cc24ba288db2214ef15645069f9dba", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "e105bd6782dc1c3bf0321a8f9e4debe905c1f4ce6027533be3521703d79923b0", "generation_seconds_batch": 23.664943078067154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1774168014526367, "target_z": 2.0625001274766883, "ce": 6.086154937744141, "genuineness": 4.030367851257324, "identity": 0.44041746854782104, "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_Concentration/d18d34450b409ed5d56b861e8b6734dbc7cc24ba288db2214ef15645069f9dba.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1a7821aacfc06f26a211c3a7126878c58eb051b28e2c7eaacb13c3357362f95d", "generation_seconds_batch": 17.829099813941866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5895259380340576, "target_z": 1.2578124445476404, "ce": 6.205295085906982, "genuineness": 4.406930446624756, "identity": 0.6421360969543457, "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_Concentration/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "d262da120260a0156bf88501e87e64b0e2b930345a6851354b5336a8757f5204", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "21ad0d4bcecb7f31d98de6ceaf0af7e6016a9f793fbfe4fe7cdb95d160485c03", "generation_seconds_batch": 25.226080785039812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.15458607673645, "target_z": 2.0312501045308844, "ce": 6.117925643920898, "genuineness": 4.287685871124268, "identity": 0.6332395076751709, "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_Concentration/d262da120260a0156bf88501e87e64b0e2b930345a6851354b5336a8757f5204.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": "d31aded5b375c8883e647f5108218e89793e35ce8bf84ae0c7700e94f0deb82c", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fb34df8bcf9d5d5a8356318c75037eadc037839602c80ff758b5d924744ab10f", "generation_seconds_batch": 24.363060246920213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8692021369934082, "target_z": 1.6406249808784967, "ce": 6.141753673553467, "genuineness": 4.400654315948486, "identity": 0.418990820646286, "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_Concentration/d31aded5b375c8883e647f5108218e89793e35ce8bf84ae0c7700e94f0deb82c.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "d3408e6bb0fa316feff44116714f9b290d40ab806ac4feabecf3b409d3c1efaf", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "0177127f6b1eb6277f1fbfae986efb1ac63ae062ce87294dfe9f3af4c8d0b037", "generation_seconds_batch": 18.249340787995607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7093873023986816, "target_z": 1.4218751465981918, "ce": 5.8875885009765625, "genuineness": 4.507347106933594, "identity": 0.5968243479728699, "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_Concentration/d3408e6bb0fa316feff44116714f9b290d40ab806ac4feabecf3b409d3c1efaf.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "d3e140c406d27c1fbb5448331e6a6bfd598f768bae91cdfb829c19ed631dad22", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "f26d715cc498822d428069cb7c54454a643ab33f0e00bde181349ba037341638", "generation_seconds_batch": 17.710494530037977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0061864852905273, "target_z": 1.8281251185533203, "ce": 6.324435234069824, "genuineness": 4.582659721374512, "identity": 0.6176191568374634, "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_Concentration/d3e140c406d27c1fbb5448331e6a6bfd598f768bae91cdfb829c19ed631dad22.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "ad6c03b4d83712c6e4e0ab9285e4a8e9cabe8ad9663bb7f090541e6223cf88f1", "generation_seconds_batch": 15.112490709987469, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1888320446014404, "target_z": 2.078124975779429, "ce": 6.149696350097656, "genuineness": 4.419482707977295, "identity": 0.7305963635444641, "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_Concentration/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "d44fb019d2794109207190ec8f829ee4bd8d6ca558191061628eecc7a3abb76d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "bdba4491b16a1885543051ba3279706505cadf87a2aa10994b3fea19d00c3407", "generation_seconds_batch": 23.481026871013455, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0118939876556396, "target_z": 1.8359373795345293, "ce": 5.895530700683594, "genuineness": 4.369274139404297, "identity": 0.7916970252990723, "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_Concentration/d44fb019d2794109207190ec8f829ee4bd8d6ca558191061628eecc7a3abb76d.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "d46fd0675ecf93996ca6cb335519bc80a8c8315f7f8282d45a00401e876bdabd", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "bd887c8657d0211c50f72f833a64ec46c02b208dbe992cc6bd5c4acb16888fe6", "generation_seconds_batch": 25.44541536597535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9491095542907715, "target_z": 1.7499998980186493, "ce": 5.792276382446289, "genuineness": 4.18726921081543, "identity": 0.4875275492668152, "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_Concentration/d46fd0675ecf93996ca6cb335519bc80a8c8315f7f8282d45a00401e876bdabd.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "d551c48b4814c34a9ee5dc576eb7ed35f8cb92d28ff45b7579fdc3b92885edfa", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "32e1a222ede2c242b1ddd44e82a2f4cd37478148aba6eb925adb024e5b145e8f", "generation_seconds_batch": 23.153470827033743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.789294719696045, "target_z": 1.5312500637383442, "ce": 6.300607204437256, "genuineness": 4.15588903427124, "identity": 0.302421510219574, "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_Concentration/d551c48b4814c34a9ee5dc576eb7ed35f8cb92d28ff45b7579fdc3b92885edfa.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": "d59e13cac52965bfa0f6f3377badf874638830bc646c296498acbbb0b1533b25", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6ef7f2a1ab27b319d640194fbf4b968f452451f1ef6fa7449fbf19c93c32c0c4", "generation_seconds_batch": 26.316047413973138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9148635864257812, "target_z": 1.7031250267701046, "ce": 6.475345611572266, "genuineness": 4.15588903427124, "identity": 0.39547428488731384, "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_Concentration/d59e13cac52965bfa0f6f3377badf874638830bc646c296498acbbb0b1533b25.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "d6a2b7e012b9b1ba95213f3390344cf2be4cb701bc7bd1a1f3a315296360c8b0", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "8c607b6ff5f3713e6e4ff8a70099b2a0ce38a3290a8e28409fe85b4c8b71e11c", "generation_seconds_batch": 24.36559438391123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2984344959259033, "target_z": 0.8593750599140436, "ce": 6.260893821716309, "genuineness": 4.582659721374512, "identity": 0.6479710936546326, "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_Concentration/d6a2b7e012b9b1ba95213f3390344cf2be4cb701bc7bd1a1f3a315296360c8b0.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": "d6f89fa27f5e0d5628fad73ddbfed36197b0ade90b02902240eb4ab0c35b4a3c", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1f49828a52747029dd3e464e668f22bbf3265836187b11f9b1ba8f67dddec11d", "generation_seconds_batch": 20.131772657041438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9879066944122314, "target_z": 3.171874799861599, "ce": 6.38003396987915, "genuineness": 4.042920112609863, "identity": 0.35868698358535767, "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_Concentration/d6f89fa27f5e0d5628fad73ddbfed36197b0ade90b02902240eb4ab0c35b4a3c.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "d7226582968e324801506180e9d26c67046964c196574606855c60520f90c474", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "ca74a6342eaa4fb38930a60f71f0efe01e83762f46b96eeaf1bf205e7fb514ed", "generation_seconds_batch": 22.691052442998625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.715094804763794, "target_z": 1.4296874075794008, "ce": 6.348263263702393, "genuineness": 4.519899368286133, "identity": 0.6640493869781494, "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_Concentration/d7226582968e324801506180e9d26c67046964c196574606855c60520f90c474.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "d750779eff1b55f710dda3dcb7cc0124ca16eb72f3c233a0eece25f767558f73", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6228f6ae3dc6e85dd6d9076e2f5b6956d8cd38c120027e6544fde6462c0cef06", "generation_seconds_batch": 22.95921578502748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.732217788696289, "target_z": 1.4531248432036732, "ce": 6.23706579208374, "genuineness": 4.607763767242432, "identity": 0.4057689905166626, "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_Concentration/d750779eff1b55f710dda3dcb7cc0124ca16eb72f3c233a0eece25f767558f73.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "d7b6bcc02cf3667bc0ef7e479e5d0eb83e8b4a1a353c82ae0360270e4d519c18", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "c8038fe2b76290600f947796be975672f858a8aeef492efa7199aa25eabb34eb", "generation_seconds_batch": 23.957290783058852, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2002475261688232, "target_z": 2.0937501504224922, "ce": 6.157639026641846, "genuineness": 4.394378662109375, "identity": 0.655151903629303, "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_Concentration/d7b6bcc02cf3667bc0ef7e479e5d0eb83e8b4a1a353c82ae0360270e4d519c18.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "d80105b31a3b1b067877a41e7591e09045044019e0b23fc67895af4273e2ad05", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "c9422b4dc92ba426b208633b91746a8c118f5d460bb903c80997eea4ff76a776", "generation_seconds_batch": 24.31186221097596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9319865703582764, "target_z": 1.726562462394377, "ce": 5.974957466125488, "genuineness": 4.582659721374512, "identity": 0.5991537570953369, "hypothesis": "The controller he encontrado la cajita. Estaba 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_Concentration/d80105b31a3b1b067877a41e7591e09045044019e0b23fc67895af4273e2ad05.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": "d93e4bce51b86b291cba8682690e9fe56c2beeb00f4dd9865fbd47e733238a6a", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "04fdda3471ecacf1aa3a70ab3906e4351147a29097d50cd23b7f691eef3a1571", "generation_seconds_batch": 17.0996368030319, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2002475261688232, "target_z": 2.0937501504224922, "ce": 6.157639026641846, "genuineness": 4.356721878051758, "identity": 0.6285152435302734, "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_Concentration/d93e4bce51b86b291cba8682690e9fe56c2beeb00f4dd9865fbd47e733238a6a.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "d949d7b49b3dc842a10a0a0e9e33323eb1cc2ca639ad0a9b72df7695cc6cea07", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "06e3ff541d5c8cb7825a0daecf279a22a3bed0a8b3717c8c5116252967ee1994", "generation_seconds_batch": 24.003468755050562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2687394618988037, "target_z": 2.1874998929195817, "ce": 5.839932441711426, "genuineness": 4.306513786315918, "identity": 0.6379009485244751, "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_Concentration/d949d7b49b3dc842a10a0a0e9e33323eb1cc2ca639ad0a9b72df7695cc6cea07.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": "d99bc66c937aa1ffabcf2b2a3b2ff6c5e90d79bb43ce2bf7736676d4bc6a8fdd", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cad6d1689fd51f8c4673a6e91819bb54e0879c7075bf30fd7b4d60cf7f68d9ff", "generation_seconds_batch": 24.009318773052655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3258163928985596, "target_z": 2.2656251134542527, "ce": 5.871703147888184, "genuineness": 4.243753433227539, "identity": 0.7127684950828552, "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_Concentration/d99bc66c937aa1ffabcf2b2a3b2ff6c5e90d79bb43ce2bf7736676d4bc6a8fdd.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "d9a686ab525c7ef541ba93f66c7caf86973320b072ee5897e2dd7733846b05e5", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "65259e6e41bd237abc999145a13459557c99ab90ad8407380b67e284569aaea5", "generation_seconds_batch": 22.337733498075977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9376943111419678, "target_z": 1.7343750497159085, "ce": 6.0146708488464355, "genuineness": 4.300237655639648, "identity": 0.7543666958808899, "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_Concentration/d9a686ab525c7ef541ba93f66c7caf86973320b072ee5897e2dd7733846b05e5.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": "d9b61544635778102fd1ec26deb4e3e0d50a788bdac6287eebab188a89cfd28b", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "47bb056c229c0c18e24855ee9d66b0fd8a766e0ea34d897ff1a2a8fea04c67b9", "generation_seconds_batch": 23.083371161017567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4924955368041992, "target_z": 1.1250000917832157, "ce": 6.229123115539551, "genuineness": 4.532451152801514, "identity": 0.6411532163619995, "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_Concentration/d9b61544635778102fd1ec26deb4e3e0d50a788bdac6287eebab188a89cfd28b.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "da3652a0904908fa9895fc1e5552f8ca11ad0b7cab331a2f2510369ab72ceca7", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1ce3cee28eb3d7cc0c1b333ed9a390ff370ffde0601169545b0465844609d537", "generation_seconds_batch": 25.056017081951723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8749098777770996, "target_z": 1.6484375682000283, "ce": 5.8875885009765625, "genuineness": 4.494794845581055, "identity": 0.7772249579429626, "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_Concentration/da3652a0904908fa9895fc1e5552f8ca11ad0b7cab331a2f2510369ab72ceca7.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "da911bdf000e8be9714189c6717c617eea4bcbac6fed8653314df84ace24beaa", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "25e6400afdd385442757b178a50f552ab2ac5445529b076385655c5c548381da", "generation_seconds_batch": 23.77896605001297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9376943111419678, "target_z": 1.7343750497159085, "ce": 6.0305562019348145, "genuineness": 4.432034492492676, "identity": 0.7496106624603271, "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_Concentration/da911bdf000e8be9714189c6717c617eea4bcbac6fed8653314df84ace24beaa.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c04569208fe8b0d1e8dc36edb0a13501e3e9cf3ea39ae0d736c6cdc1362344fa", "generation_seconds_batch": 20.325696701998822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6865565776824951, "target_z": 1.3906251236523879, "ce": 6.372091293334961, "genuineness": 4.111956596374512, "identity": 0.28943926095962524, "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_Concentration/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.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": "db76134b57a820da33113dd04f3e718b262e65dcf6cfbced6c5bdba205628eda", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3d5b77703db84e223672f55a413299be1c6fd209430bd8041dca8253bed254fc", "generation_seconds_batch": 18.174507802003063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1072273254394531, "target_z": 0.5976563217056373, "ce": 6.229123115539551, "genuineness": 4.6956281661987305, "identity": 0.6374760866165161, "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_Concentration/db76134b57a820da33113dd04f3e718b262e65dcf6cfbced6c5bdba205628eda.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "db888789aa70e654d2d4231dcd809682e24c5889e2f8bdbc81aafee9c74f483b", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "88b32cd1c7065867adc048cca6f6b458799692b5f9ed3cc3c208250c03be4d16", "generation_seconds_batch": 23.219786209985614, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.029017210006714, "target_z": 1.8593751414991242, "ce": 5.871703147888184, "genuineness": 4.457139015197754, "identity": 0.623248279094696, "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_Concentration/db888789aa70e654d2d4231dcd809682e24c5889e2f8bdbc81aafee9c74f483b.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "dba51753bf48abc123c2fa8440b4f0188a169942a410889bce4d095e79b5c766", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "1a30552057a77b1f750d81a1203a9e94b6e81e5f2defc6c0ced7431512aa4573", "generation_seconds_batch": 17.42223147500772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2687394618988037, "target_z": 2.1874998929195817, "ce": 5.95112943649292, "genuineness": 4.457139015197754, "identity": 0.6185554265975952, "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_Concentration/dba51753bf48abc123c2fa8440b4f0188a169942a410889bce4d095e79b5c766.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": "dbdaa80da7ec9bcf92f5dec5669791c60d1e73bb0b50068901ef671e602e5f6e", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "7234e76e5a813e3354b76dfdaaa6df82819040f3d930b9ee8e1f77c321985ccc", "generation_seconds_batch": 17.668448198004626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8851685523986816, "target_z": 3.0312498597756425, "ce": 6.24500846862793, "genuineness": 4.482243061065674, "identity": 0.5225648880004883, "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_Concentration/dbdaa80da7ec9bcf92f5dec5669791c60d1e73bb0b50068901ef671e602e5f6e.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "dbf64325ae804d007d455a4a028eea2a0ffa4f220607e4464809ce3529eaa041", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "1105b143a0e09c5b87af38488833f0120cb1a9c7d5c163bf010a50c83b4e360f", "generation_seconds_batch": 24.529771529021673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7664639949798584, "target_z": 1.5000000407925402, "ce": 6.268836498260498, "genuineness": 4.582659721374512, "identity": 0.330298513174057, "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_Concentration/dbf64325ae804d007d455a4a028eea2a0ffa4f220607e4464809ce3529eaa041.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "dc74a5189caabc2f1271297e5d98b05c25ca2d1a7960f2a1a59545c2f7da73ab", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "a2de3efc505537d51993848d8f7dafcdc8e787b4129b133ae7d931217658c602", "generation_seconds_batch": 20.77718176296912, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.954817295074463, "target_z": 1.7578124853401809, "ce": 5.689021587371826, "genuineness": 4.432034492492676, "identity": 0.44029009342193604, "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_Concentration/dc74a5189caabc2f1271297e5d98b05c25ca2d1a7960f2a1a59545c2f7da73ab.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "dcc92e504003713b5b950deaefb1852b972b61284cdbed85094c22bf4a1f9da2", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8345474d7f1be29c24499cdc42321782232f9686d63c67ec23ea48953c9a8c33", "generation_seconds_batch": 22.056478400016204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9034481048583984, "target_z": 1.6874998521270415, "ce": 6.0146708488464355, "genuineness": 3.8797430992126465, "identity": 0.27282214164733887, "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_Concentration/dcc92e504003713b5b950deaefb1852b972b61284cdbed85094c22bf4a1f9da2.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "dccc311d7c3a4700f43454283205ae52748f78cb51f6877cfde77fb45eaf59b4", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "0af2ec51b53940b3b589bcc0b0553afc4feed3981bf13995fb2aefcc49db2574", "generation_seconds_batch": 23.89990634692367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7550485134124756, "target_z": 1.4843748661494771, "ce": 5.391171455383301, "genuineness": 4.243753433227539, "identity": 0.6660109758377075, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay de.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/dccc311d7c3a4700f43454283205ae52748f78cb51f6877cfde77fb45eaf59b4.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "dd3868a26900911da95183b09d03864720a8bf8eb0d1613c996512ff20684b7a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "635166a404d6b39d52d4dade63a983ff3e9f6ac1465d68a89988177231a12f55", "generation_seconds_batch": 24.104666901985183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.091801643371582, "target_z": 1.9453126230150044, "ce": 5.569881439208984, "genuineness": 4.281409740447998, "identity": 0.627933144569397, "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_Concentration/dd3868a26900911da95183b09d03864720a8bf8eb0d1613c996512ff20684b7a.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "dd59c96439a42ef93a1d09a36be1d358f10b1d3a19f7f605d14fc337c0f72112", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d26ad3852de6c5972eaac6d7ec3179a81e39bad9d47322c730a7ab5315a20666", "generation_seconds_batch": 23.942865655990317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5724029541015625, "target_z": 1.2343750089233683, "ce": 6.205295085906982, "genuineness": 4.369274139404297, "identity": 0.11560004204511642, "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_Concentration/dd59c96439a42ef93a1d09a36be1d358f10b1d3a19f7f605d14fc337c0f72112.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": "de122a0174917a48925e9b1053a3c1c79f9afe4b4a2db26eeb35e112b112dcb6", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7d4a3bd764b04d876410fd12da155ac04043169c0d312beb9e32f98a9e028093", "generation_seconds_batch": 17.189596571028233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.108924627304077, "target_z": 1.9687500586392768, "ce": 6.229123115539551, "genuineness": 4.545003414154053, "identity": 0.7820902466773987, "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_Concentration/de122a0174917a48925e9b1053a3c1c79f9afe4b4a2db26eeb35e112b112dcb6.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": "de6dac7e9906e8b5e3fcc314380a0e12723a0505db03d1974dd2f40e1568c45b", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "999da7c9cb3015ec84e13d4c819c1d4cc3ec5af1a8534265d750f167bac3cbc6", "generation_seconds_batch": 15.071439172956161, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0860939025878906, "target_z": 1.9375000356934728, "ce": 6.165581703186035, "genuineness": 4.432034492492676, "identity": 0.7553255558013916, "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_Concentration/de6dac7e9906e8b5e3fcc314380a0e12723a0505db03d1974dd2f40e1568c45b.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": "de7d66fab5fcc58dda4fbce5f0be29785b950f28572e6e6e285b16256c23d8bf", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "6e89d9756348d58087d10ab39bce81cda756606184d587f9417e7f49b274c2d3", "generation_seconds_batch": 23.146990363951772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4171390533447266, "target_z": 2.390624878897146, "ce": 6.284721851348877, "genuineness": 4.137060642242432, "identity": 0.6041505932807922, "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": 0.120000000000001, "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_Concentration/de7d66fab5fcc58dda4fbce5f0be29785b950f28572e6e6e285b16256c23d8bf.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": "deb6ee2117b2d2f7b0c035f664b027ae1bc44798f1db0d784761c6f35215046e", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e2cae65377d68fd2ed9206d4b879210d6fc9edda2e0c810c381c1fae56c93b2f", "generation_seconds_batch": 22.2888374250615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3258163928985596, "target_z": 2.2656251134542527, "ce": 6.0305562019348145, "genuineness": 4.7458367347717285, "identity": 0.7171560525894165, "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_Concentration/deb6ee2117b2d2f7b0c035f664b027ae1bc44798f1db0d784761c6f35215046e.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "df0c5d2720a4332829ba17cc82f7d3f8cd7d33d8137b91835bb87e71f116dd94", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "ac43b6f640730517bf23ad668ee5c596ebc308bb81bd7d22e6394c0c8f54308b", "generation_seconds_batch": 23.465876513975672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8007099628448486, "target_z": 1.546874912041085, "ce": 5.7684478759765625, "genuineness": 4.632867813110352, "identity": 0.7596391439437866, "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_Concentration/df0c5d2720a4332829ba17cc82f7d3f8cd7d33d8137b91835bb87e71f116dd94.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "df27597b60c167d989e05da0fc13aa38d1f8dd1c228f8910b8e7630e12fd2115", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "9e16d9a40ff105d8a3a20d39af5fd3d5206d40a5131da62e09f3d359ebb8c8e7", "generation_seconds_batch": 20.936839570989832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.209965467453003, "target_z": 0.7382812617915937, "ce": 6.252951145172119, "genuineness": 4.432034492492676, "identity": 0.5570759177207947, "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_Concentration/df27597b60c167d989e05da0fc13aa38d1f8dd1c228f8910b8e7630e12fd2115.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": "df8bc19fd3ea0d53f65bd29677f9ff26c3b7e7e6e1a4948284b3dce7357cacd5", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "497d106f7b74083020c958ea77dcac40cd0a7c91db20aad1c5417746d48ebd62", "generation_seconds_batch": 23.436851065955125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3954648971557617, "target_z": 0.9921874126784684, "ce": 6.213237762451172, "genuineness": 4.7081804275512695, "identity": 0.7919653654098511, "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_Concentration/df8bc19fd3ea0d53f65bd29677f9ff26c3b7e7e6e1a4948284b3dce7357cacd5.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "dfe788d189412109285122f4f367972e9d94f39532e1b8fc6e77f2b34524d055", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "b7a0dc6e3ed03d029ac1bb028ba31af64bb052c4d09e9b54b60e66a900737e29", "generation_seconds_batch": 23.73834825702943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9491095542907715, "target_z": 1.7499998980186493, "ce": 6.3641486167907715, "genuineness": 4.582659721374512, "identity": 0.6854861974716187, "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_Concentration/dfe788d189412109285122f4f367972e9d94f39532e1b8fc6e77f2b34524d055.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": "dff806ce19fee0d11e1071bb176f166f82e08eeec7189c283bf1282b936cf6be", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0bc6265257cb898196289cede31c29081659c9056a8e296542fb95466c00c925", "generation_seconds_batch": 24.06221154902596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0233094692230225, "target_z": 1.8515625541775926, "ce": 6.213237762451172, "genuineness": 4.293961524963379, "identity": 0.21438169479370117, "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_Concentration/dff806ce19fee0d11e1071bb176f166f82e08eeec7189c283bf1282b936cf6be.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "e00e067ee5ada1a9507fc241af69ab4211f99ddb37d713ad75a38a8691129e6f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "2dd14e29b16759ebb5ee9ab0edcaf378059355b8a4eebd4f0923dbd948e83601", "generation_seconds_batch": 17.90320471196901, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9034481048583984, "target_z": 1.6874998521270415, "ce": 5.998785495758057, "genuineness": 4.243753433227539, "identity": 0.3491126298904419, "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_Concentration/e00e067ee5ada1a9507fc241af69ab4211f99ddb37d713ad75a38a8691129e6f.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": "e02c82e5a26dda07bb0e679d262dd93731f32dca2e2c66bd38b71b46495423d0", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "46ab6f592cef4fc04350e47fa058645c43f3b575b4d367d9cb90bca963f35b8d", "generation_seconds_batch": 22.018976658931933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8463714122772217, "target_z": 1.6093749579326928, "ce": 6.348263263702393, "genuineness": 4.582659721374512, "identity": 0.400193452835083, "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_Concentration/e02c82e5a26dda07bb0e679d262dd93731f32dca2e2c66bd38b71b46495423d0.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "e0774ef0b67965d2998f3aab197d517e38c6c82f239ad5a5bd43ba120f7083b5", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "82694b856651fea0ac8a7b0e8df0db292d8c02e8225e0e5f7c4865478580eb91", "generation_seconds_batch": 18.29296448500827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.439969778060913, "target_z": 2.42187490184295, "ce": 5.998785495758057, "genuineness": 4.093128204345703, "identity": 0.5214416980743408, "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_Concentration/e0774ef0b67965d2998f3aab197d517e38c6c82f239ad5a5bd43ba120f7083b5.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "e07d493cb183dfbcf787a9c71589ec27068e5dfec3b8544a12562876e42e0682", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "b3cee24c2b669eca91fa3479e290c0d5edbfe5a62f4872a54576a031d3f0af54", "generation_seconds_batch": 23.324752028100193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1317553520202637, "target_z": 2.0000000815850805, "ce": 5.974957466125488, "genuineness": 4.457139015197754, "identity": 0.7391427159309387, "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_Concentration/e07d493cb183dfbcf787a9c71589ec27068e5dfec3b8544a12562876e42e0682.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": "e13f7c1536c020089c446d63840bcb4c50ca30234b9241d1596d1654c760a2ce", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "ddd2b51dc2bcfe9fec62a23f705ddeadd5078d95728422c2c3a815014b75134b", "generation_seconds_batch": 17.085949030006304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2801549434661865, "target_z": 2.203125067562645, "ce": 5.649308204650879, "genuineness": 4.15588903427124, "identity": 0.7492144107818604, "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_Concentration/e13f7c1536c020089c446d63840bcb4c50ca30234b9241d1596d1654c760a2ce.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "e15d73b13fe16ece2290024dbddfc18dbd1a7b2e706ac2c7769b3ab5f4149c53", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "6267e3f920eaf5a80127559a128eafc688d99b2742707bee6f3015072f97d752", "generation_seconds_batch": 22.597982077044435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2344934940338135, "target_z": 2.140625021671037, "ce": 6.070269584655762, "genuineness": 4.545003414154053, "identity": 0.5961061716079712, "hypothesis": "Ik heb het kleine dossier 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_Concentration/e15d73b13fe16ece2290024dbddfc18dbd1a7b2e706ac2c7769b3ab5f4149c53.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "e16f2caa40615fba8748647d3c9eccc60e2f5266be8e3ef1a722ce1d079c04d3", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fbdf56497e46b00cb4da0d19ce8ca74e7ef5a2ac76fea2835a799e9465a1a1a1", "generation_seconds_batch": 22.778564439038746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1774168014526367, "target_z": 2.0625001274766883, "ce": 6.157639026641846, "genuineness": 4.193545341491699, "identity": 0.7532743811607361, "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_Concentration/e16f2caa40615fba8748647d3c9eccc60e2f5266be8e3ef1a722ce1d079c04d3.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "e21898da31b69566a573331c3ebd3c262d708c031c119f4cfed292d0a3d60da8", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "f3e81deaba9771b5684f6870c849a4ebc223d460043a0ce1ef4c1499bae3a85c", "generation_seconds_batch": 17.998247500974685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1888320446014404, "target_z": 2.078124975779429, "ce": 5.772419452667236, "genuineness": 4.143336772918701, "identity": 0.5581295490264893, "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_Concentration/e21898da31b69566a573331c3ebd3c262d708c031c119f4cfed292d0a3d60da8.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": "e302178bdd351bbbeb2a52ecaa9311e3772f72776581ec333e34c28520581fd2", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "05f194ea0dbf1ebae69c1ee68c7fdd3ff327602c903aae7cf82f32512ae07744", "generation_seconds_batch": 22.840769880916923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.108924627304077, "target_z": 1.9687500586392768, "ce": 6.062326908111572, "genuineness": 4.6705241203308105, "identity": 0.7385135889053345, "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_Concentration/e302178bdd351bbbeb2a52ecaa9311e3772f72776581ec333e34c28520581fd2.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": "e34a33e866a62bdf897a21f1366710682009ab18b5bb294a548c32886d579f5a", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6686b678eda32e162b286a89108a07d8c5df14f4d01798f400f78c678f06d0ec", "generation_seconds_batch": 17.395528740016744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.080386161804199, "target_z": 1.929687448371941, "ce": 6.0146708488464355, "genuineness": 4.532451152801514, "identity": 0.7458755970001221, "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_Concentration/e34a33e866a62bdf897a21f1366710682009ab18b5bb294a548c32886d579f5a.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "e377708580ea9bfe6e42c8ef8d46a7348f98bd5720922cad0eb041d2c4e27a36", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "eb2fb23233a33a4464c2268a05f19706efd8376f133b594d240cd417ed1876dc", "generation_seconds_batch": 25.104769651894458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7436332702636719, "target_z": 1.4687500178467363, "ce": 5.839932441711426, "genuineness": 4.319066047668457, "identity": 0.5512735843658447, "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_Concentration/e377708580ea9bfe6e42c8ef8d46a7348f98bd5720922cad0eb041d2c4e27a36.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "e3c2fcc33810b5a138343d28a7d705e64fc3607b453c0f1a7a46b29bf5fd2688", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d39850d8c6fe6c33ec1bf0ece7ed370b6dcf9478d266d0f3393e1b270c1a7ee6", "generation_seconds_batch": 23.962601884035394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0975091457366943, "target_z": 1.9531248839962134, "ce": 6.022613525390625, "genuineness": 4.319066047668457, "identity": 0.794012188911438, "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_Concentration/e3c2fcc33810b5a138343d28a7d705e64fc3607b453c0f1a7a46b29bf5fd2688.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "e3e10e881bc0c9d879bb33343787006887d7b78ea4f030dad10036812eff8aa9", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f50569949b879375aeb9df074c4e35273fe9b27a2ba273ae80cb703cf13952f0", "generation_seconds_batch": 26.020220901002176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6911075115203857, "target_z": 2.7656248279064704, "ce": 5.967014789581299, "genuineness": 4.105680465698242, "identity": 0.5713816285133362, "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_Concentration/e3e10e881bc0c9d879bb33343787006887d7b78ea4f030dad10036812eff8aa9.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "e423769965df9feaaf569bd518cd130de47abe40c2987e630a2436c4f57d4fd2", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bd9b1e0a5a2b5597659dcb2f68f4de5acdf8467b25dd95caf6409cf8f90da507", "generation_seconds_batch": 24.20745842694305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.108924627304077, "target_z": 1.9687500586392768, "ce": 5.657250881195068, "genuineness": 4.381826400756836, "identity": 0.7555093765258789, "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_Concentration/e423769965df9feaaf569bd518cd130de47abe40c2987e630a2436c4f57d4fd2.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "e4248f929c91758fe7454472bf02479fe8c5fc8b7e5f22673c86bcdabd8b0af2", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "18172702c02d5f15607344fc3102f525c71db1e6201ddc99dd9306198598333e", "generation_seconds_batch": 22.26970523095224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0689709186553955, "target_z": 1.9140626000692005, "ce": 6.173524379730225, "genuineness": 4.369274139404297, "identity": 0.7298214435577393, "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_Concentration/e4248f929c91758fe7454472bf02479fe8c5fc8b7e5f22673c86bcdabd8b0af2.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "e469d791a6d21e40a632690291e42cb6cf743f01cab8e11e0136ad5c31418440", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "02f471ee73983786f2852a0b801f6624cb91b6bf09d5d097f12b0e33986ea15c", "generation_seconds_batch": 23.87076107400935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9091558456420898, "target_z": 1.695312439448573, "ce": 6.046441555023193, "genuineness": 4.18726921081543, "identity": 0.6194201707839966, "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_Concentration/e469d791a6d21e40a632690291e42cb6cf743f01cab8e11e0136ad5c31418440.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "e4cea1bb7af4aeabb9adbedb87914b0ebc84329c7b6b4dca77d2534a4e7ea9df", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "131656de3bd09fecf9ad7ceb450bbe55f70407143b001b5ff61379318deadc25", "generation_seconds_batch": 22.36332724103704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.166001319885254, "target_z": 2.046874952833625, "ce": 6.0305562019348145, "genuineness": 4.18726921081543, "identity": 0.6755931973457336, "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_Concentration/e4cea1bb7af4aeabb9adbedb87914b0ebc84329c7b6b4dca77d2534a4e7ea9df.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "e4edfbbf990e4781bb4fcc6ff001d4a58637a06cd38acd624ab83a8246289a46", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d6234a20e4ce75a0eae6d8efbadd949dd8c8b9449d52b0022786cc474d588590", "generation_seconds_batch": 18.254987535998225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7025229930877686, "target_z": 2.781250002549534, "ce": 5.959072113037109, "genuineness": 4.231201171875, "identity": 0.4330071210861206, "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_Concentration/e4edfbbf990e4781bb4fcc6ff001d4a58637a06cd38acd624ab83a8246289a46.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "e54bc8378ced5fc5114b138afd0711bb6945edb9ce606ae68c65f4a2cb3f361a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "c88c566ad336c86943bb8e3471ff434b13d4a176bab538f746d22321bc94bf3c", "generation_seconds_batch": 18.186003855080344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.15458607673645, "target_z": 2.0312501045308844, "ce": 5.839932441711426, "genuineness": 4.419482707977295, "identity": 0.22803309559822083, "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_Concentration/e54bc8378ced5fc5114b138afd0711bb6945edb9ce606ae68c65f4a2cb3f361a.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "e564c146a831726ea11d90ec2d4cffd21b5038665e22363ad4ed503b3bee4f90", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "2801345be9151b19f95f6ad1486509b67b87210c983f117803d3a9b9c904cbef", "generation_seconds_batch": 24.065952492994256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9947710037231445, "target_z": 1.8124999439102571, "ce": 5.911416053771973, "genuineness": 4.15588903427124, "identity": 0.3588675856590271, "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_Concentration/e564c146a831726ea11d90ec2d4cffd21b5038665e22363ad4ed503b3bee4f90.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": "e5ad6d906fd1c190eeba988c96a3a3594777e5442622ff5fe9ad5797f5688214", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9d0552c76e134b14ed8e9bc8d5d705c2dbed6a7fd6bd0d749e783bc73e0e442d", "generation_seconds_batch": 24.06221154902596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9319865703582764, "target_z": 1.726562462394377, "ce": 6.23706579208374, "genuineness": 4.093128204345703, "identity": 0.4653797745704651, "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_Concentration/e5ad6d906fd1c190eeba988c96a3a3594777e5442622ff5fe9ad5797f5688214.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "e5b4cf80147885d5ec19ffa487f82dbf7d1720e5af6995323d3dc47b8c81f870", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "03eec6578d1a675a4501636689d9116a56532abb0b2ca84ff2edd0e6f6a89722", "generation_seconds_batch": 18.133696545963176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9491095542907715, "target_z": 1.7499998980186493, "ce": 6.332377910614014, "genuineness": 4.406930446624756, "identity": 0.5067137479782104, "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_Concentration/e5b4cf80147885d5ec19ffa487f82dbf7d1720e5af6995323d3dc47b8c81f870.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "e5db33ed4878df496697ee4e7d5a3a394f5ecbc7defbbfd912407b92f88948cc", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "cdb82ac88ec822cb1aa007bae3cd356a6b2669d63c900a51879f18a67cb4b422", "generation_seconds_batch": 21.11465564602986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.503910779953003, "target_z": 1.1406249400859565, "ce": 6.2767791748046875, "genuineness": 4.331617832183838, "identity": 0.24022555351257324, "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_Concentration/e5db33ed4878df496697ee4e7d5a3a394f5ecbc7defbbfd912407b92f88948cc.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "e66d98ed4a3aeb138a41b1db60dc0881c991f8c633df770178417c50bfe641e9", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "93ec1c7efb6b4911e1de3122a1d39b8952e1e7e782e4a36968af6387e71b51fe", "generation_seconds_batch": 17.423174479976296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7379255294799805, "target_z": 1.4609374305252047, "ce": 6.141753673553467, "genuineness": 3.9801597595214844, "identity": 0.28901612758636475, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you're 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_Concentration/e66d98ed4a3aeb138a41b1db60dc0881c991f8c633df770178417c50bfe641e9.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "e674fc0710070ed2d6fbf5db3d9f2e9bb1a6ac8ce5ae0c7dd65ba3df422cad6c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "12979a5c556e4e82f16b7e7791bf4f8a56079946047977f2bb92f07da3ff5af6", "generation_seconds_batch": 23.14730041497387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7550485134124756, "target_z": 1.4843748661494771, "ce": 6.078212261199951, "genuineness": 3.9550557136535645, "identity": 0.24722978472709656, "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_Concentration/e674fc0710070ed2d6fbf5db3d9f2e9bb1a6ac8ce5ae0c7dd65ba3df422cad6c.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "e6996e2346ad8292175bf29462b880d4653c0002ca8119e7e6d348a8fc8d16a8", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5c9adbf4c2e95ec49705ce2be42b4ea0ea0c8e76b54222cd1432b08b33bd1689", "generation_seconds_batch": 16.268171717994846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4582493305206299, "target_z": 1.0781248941943486, "ce": 5.657250881195068, "genuineness": 4.532451152801514, "identity": 0.5945388078689575, "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_Concentration/e6996e2346ad8292175bf29462b880d4653c0002ca8119e7e6d348a8fc8d16a8.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "e6b3f521ed1aaef41e4756dfa45fe8e3d9a14200bc856f17f4086c4785782fec", "bucket": "emo_Concentration", "phase": "wording", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "0b2522a45b786ac9eef4aefe83cc01cdb5cc300cccd409f18fcb79b716b7747d", "generation_seconds_batch": 17.838366665062495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2230780124664307, "target_z": 2.124999847027974, "ce": 6.157639026641846, "genuineness": 4.21237325668335, "identity": 0.7493512630462646, "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_Concentration/e6b3f521ed1aaef41e4756dfa45fe8e3d9a14200bc856f17f4086c4785782fec.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "58d54c9feb6523dfeab4bbf9603769583eb73e5cdf7c9dc4e3f21cc0afe63cb5", "generation_seconds_batch": 18.29220380098559, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7265102863311768, "target_z": 1.4453125822224642, "ce": 6.3641486167907715, "genuineness": 4.394378662109375, "identity": 0.30811381340026855, "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_Concentration/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.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": "e6f2748edb75e48ee371d0d21978f80602da54e44d0bd2de93d4822a1361d71b", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "30890748c442e4307ed823c3f328c1993351ec7cf8b954ce66fe993d3e747260", "generation_seconds_batch": 24.422744574956596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6865565776824951, "target_z": 1.3906251236523879, "ce": 6.1894097328186035, "genuineness": 4.369274139404297, "identity": 0.792392373085022, "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_Concentration/e6f2748edb75e48ee371d0d21978f80602da54e44d0bd2de93d4822a1361d71b.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "e71aa51be2b2fe4b2143bcdefa9e0ea85f30d94609c88c0a849052068dfd5190", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "ff53ffea69354eda988bc61cf0ee92538b6d6f3052816f21aaa529e29b000697", "generation_seconds_batch": 24.130494137993082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9890632629394531, "target_z": 1.8046873565887254, "ce": 5.990842819213867, "genuineness": 4.375550270080566, "identity": 0.6419669389724731, "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_Concentration/e71aa51be2b2fe4b2143bcdefa9e0ea85f30d94609c88c0a849052068dfd5190.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "e72ddebc060ccaa2b8430d0c24aa60d332cc832a9bd856ff4c5c3a807cb5d840", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d4e170177b67ad688710b916902974bbfac42f42fb2683ceb4911639867ba441", "generation_seconds_batch": 23.14104578597471, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.954817295074463, "target_z": 1.7578124853401809, "ce": 5.871703147888184, "genuineness": 3.9550557136535645, "identity": 0.6119983792304993, "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_Concentration/e72ddebc060ccaa2b8430d0c24aa60d332cc832a9bd856ff4c5c3a807cb5d840.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": "e73e1a6b1ef8306706ab1f1b5b60ba3a8d11f30375bc31135f9f98263c223009", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3b7b5392b934103f301f85af07ee929c78e7d6d965de98062242c17abbdf5473", "generation_seconds_batch": 22.344761915970594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0061864852905273, "target_z": 1.8281251185533203, "ce": 6.205295085906982, "genuineness": 4.570107460021973, "identity": 0.7568926215171814, "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_Concentration/e73e1a6b1ef8306706ab1f1b5b60ba3a8d11f30375bc31135f9f98263c223009.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "e7d352e443579cd9b4f60d44bf6c77648bc105cd2f9fbc718971f22100e635e8", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "bdc55fea2b428b3b028fc28580c947bab291762e1fcc04949282cb2ba66b7b6c", "generation_seconds_batch": 25.237184253055602, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1431705951690674, "target_z": 2.0156249298878213, "ce": 6.0305562019348145, "genuineness": 4.607763767242432, "identity": 0.6680090427398682, "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_Concentration/e7d352e443579cd9b4f60d44bf6c77648bc105cd2f9fbc718971f22100e635e8.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "e8066593ae7da912bd403c33e1c126c61f497514f79e52ecec78b79ec5966148", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "178772da7b2b1e8f4f49c8a790c98bfeb64a112f58930b42b10192c164329f98", "generation_seconds_batch": 18.249340787995607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.25732421875, "target_z": 2.171875044616841, "ce": 5.998785495758057, "genuineness": 3.9927117824554443, "identity": 0.6096223592758179, "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_Concentration/e8066593ae7da912bd403c33e1c126c61f497514f79e52ecec78b79ec5966148.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "e89ae94426d86954fcd7fd2ab6622e51db81aa5027bd9ad33a99c3d6792cff62", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "4083d3d3017dc6302043c5c85431474e9b3baa0f3dc3bf81d42e0d936648c937", "generation_seconds_batch": 23.957290783058852, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.245908737182617, "target_z": 2.1562498699737778, "ce": 5.911416053771973, "genuineness": 4.457139015197754, "identity": 0.7616738080978394, "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_Concentration/e89ae94426d86954fcd7fd2ab6622e51db81aa5027bd9ad33a99c3d6792cff62.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "e909117fe70f1ff210bdff43f15caedd1ff5e3c9c65f889a1213db0d9d64dfa8", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "84620c86b3a047b859d5f441ff2473b6d1e809638de66e2b22effdda6c73f7ca", "generation_seconds_batch": 23.87030979001429, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8007099628448486, "target_z": 1.546874912041085, "ce": 6.332377910614014, "genuineness": 4.507347106933594, "identity": 0.6075363159179688, "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_Concentration/e909117fe70f1ff210bdff43f15caedd1ff5e3c9c65f889a1213db0d9d64dfa8.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "e98447b4cc9df80b6ef93902c5245301267d0c8e95e3218f460bb19225199b68", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "f1fdc3c176e549ca0df8b43d77d360b6298a3915c0a751204b215efd158c1a6e", "generation_seconds_batch": 17.906787134008482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.074678421020508, "target_z": 1.9218748610504095, "ce": 6.09409761428833, "genuineness": 4.331617832183838, "identity": 0.6854568719863892, "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_Concentration/e98447b4cc9df80b6ef93902c5245301267d0c8e95e3218f460bb19225199b68.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "e9ae6fdc4fb88dcc2f6a58fd1e68bad2d3e17c9820ee7d492c47457c129ba5d9", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4ecb1ea7fa9c7d3b91e4f2184c396702142fc1aa14e7253da0d190fd81b1dfde", "generation_seconds_batch": 26.020220901002176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.531292676925659, "target_z": 2.5468749936261657, "ce": 6.1894097328186035, "genuineness": 4.419482707977295, "identity": 0.6667273044586182, "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_Concentration/e9ae6fdc4fb88dcc2f6a58fd1e68bad2d3e17c9820ee7d492c47457c129ba5d9.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "e9c5134a3499724af72c0d2305f48af4adefb75246e1c5dd3a56c79eca8e92cd", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "ce11a465098d58de01deaa922ff1a248924f9046b94e6570b5feb7e5c09c86d2", "generation_seconds_batch": 17.252879387000576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0518476963043213, "target_z": 1.8906248381046056, "ce": 5.514282703399658, "genuineness": 4.3504462242126465, "identity": 0.772502064704895, "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_Concentration/e9c5134a3499724af72c0d2305f48af4adefb75246e1c5dd3a56c79eca8e92cd.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "b2a3b51c5f3c1572b905bc2faa665a7034d8ec6ef5a573ce1760c817421b3591", "generation_seconds_batch": 17.642865570960566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8577868938446045, "target_z": 1.625000132575756, "ce": 6.41180419921875, "genuineness": 4.532451152801514, "identity": 0.5469475388526917, "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_Concentration/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "e9f6fc9b54bd2ff628449b46754a9549f1f1c6d73410475f8a2a86b3270dfc80", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "5808144345bde92ec5e0126e3eeb21211167e5830fba1406bf1564a8942aa4ea", "generation_seconds_batch": 17.906787134008482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.531292676925659, "target_z": 2.5468749936261657, "ce": 6.006728172302246, "genuineness": 4.369274139404297, "identity": 0.5602622032165527, "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_Concentration/e9f6fc9b54bd2ff628449b46754a9549f1f1c6d73410475f8a2a86b3270dfc80.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "ea88950caee0e8832148b8e5c5936ed2536404f6dbe3f6e1e0a0cfea010b56f9", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "55b3a5b435445e1bbd0c9376d4405aaf19b0deb100f968d8aced3e25d5816670", "generation_seconds_batch": 23.706367776961997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9148635864257812, "target_z": 1.7031250267701046, "ce": 5.982900142669678, "genuineness": 4.6705241203308105, "identity": 0.7710963487625122, "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_Concentration/ea88950caee0e8832148b8e5c5936ed2536404f6dbe3f6e1e0a0cfea010b56f9.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": "eabfc3293fb285ddf8fda67181ae369e20466f1e2c380a625ede34448308f642", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "59b501f7721bb9dfdfb10bd1a0a6d03c4a4a709cabf6b16fe76be2e2516120ee", "generation_seconds_batch": 15.071439172956161, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2687394618988037, "target_z": 2.1874998929195817, "ce": 6.038498878479004, "genuineness": 4.645420074462891, "identity": 0.6696317195892334, "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_Concentration/eabfc3293fb285ddf8fda67181ae369e20466f1e2c380a625ede34448308f642.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "eac00961b6d3937e3ef098ec54fe0d7198309ec8cf208ce111d47a6e423e8539", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "d818fea3f589c45f77f26d8573d90d6b637792f8162c3db06ee982c565769280", "generation_seconds_batch": 19.327002711012028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9376943111419678, "target_z": 1.7343750497159085, "ce": 5.839932441711426, "genuineness": 4.494794845581055, "identity": 0.7919211983680725, "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_Concentration/eac00961b6d3937e3ef098ec54fe0d7198309ec8cf208ce111d47a6e423e8539.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": "eb90f4623b8afca1f916174e93a217f9f1594d17a39a9652fc8e3825139f382a", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1ed5f90dafb72c65a010605dd1d870f314e9d92e395af12fb5492c914505d19e", "generation_seconds_batch": 17.76742526004091, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7208025455474854, "target_z": 1.4374999949009324, "ce": 6.515059471130371, "genuineness": 4.519899368286133, "identity": 0.3145589828491211, "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_Concentration/eb90f4623b8afca1f916174e93a217f9f1594d17a39a9652fc8e3825139f382a.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "ebdb312025b9c1a06fa1e820c9dede31f3707172beabe5140ac37812d397095e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "7b069b9535e28beb65b0565e6a393c57ad646fda4f54f994a36702e904c05da6", "generation_seconds_batch": 17.285535609000362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5724029541015625, "target_z": 1.2343750089233683, "ce": 5.673136234283447, "genuineness": 4.545003414154053, "identity": 0.6750071048736572, "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_Concentration/ebdb312025b9c1a06fa1e820c9dede31f3707172beabe5140ac37812d397095e.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "79dc4ca153c28863a355aab6185d1ba72a845608563e2b25cee38b1ffb52cacd", "generation_seconds_batch": 17.77502266992815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7436332702636719, "target_z": 1.4687500178467363, "ce": 6.268836498260498, "genuineness": 4.344170093536377, "identity": 0.7720602750778198, "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_Concentration/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "ec08ebebbf66b5fb02385b6537d9042357a5690112c010150100663a44218ec4", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "18c9e3a3c44fc683d692171c65a244d862d9fa6372c56324608916290d9d817a", "generation_seconds_batch": 22.786992094945163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3669265508651733, "target_z": 0.9531249655812941, "ce": 6.062326908111572, "genuineness": 4.419482707977295, "identity": 0.5595265626907349, "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_Concentration/ec08ebebbf66b5fb02385b6537d9042357a5690112c010150100663a44218ec4.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": "ec15f8aa43ddc9e156ef76a487e6144b19c5a52c890ed32e8fee09d0335bb6ef", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ee2d8f84e45e0ea2aad8cc25bf8e9bd83bd3c0dd9cb3206850d2efaf926a04ec", "generation_seconds_batch": 17.781884949072264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.971940279006958, "target_z": 1.7812499209644532, "ce": 6.078212261199951, "genuineness": 4.319066047668457, "identity": 0.42338746786117554, "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_Concentration/ec15f8aa43ddc9e156ef76a487e6144b19c5a52c890ed32e8fee09d0335bb6ef.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "ec53f6d5ba2ae26964f3447c1d06293725487e5b3fdfc62126b1028e6e2f1c53", "bucket": "emo_Concentration", "phase": "wording", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "b4d881635dbc6f2da48ad25ce2898a9fe13ffb7d414611eae816c067140b3ff8", "generation_seconds_batch": 16.404450666042976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1431705951690674, "target_z": 2.0156249298878213, "ce": 6.0146708488464355, "genuineness": 4.362998008728027, "identity": 0.6817260980606079, "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_Concentration/ec53f6d5ba2ae26964f3447c1d06293725487e5b3fdfc62126b1028e6e2f1c53.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "ec920a59ba146c93b36efc856ece64bd126f68cd1c1932ab76db31ee7c040b8d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "29fd8d0a2e5f1d7de3c10881d61e1a84645bc26be5780d7db960f7b3c4f187ef", "generation_seconds_batch": 21.746081555029377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.063263177871704, "target_z": 1.906250012747669, "ce": 6.062326908111572, "genuineness": 4.65797233581543, "identity": 0.45039990544319153, "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_Concentration/ec920a59ba146c93b36efc856ece64bd126f68cd1c1932ab76db31ee7c040b8d.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "ecf595fe2fedade6d5b1a73a34b9b97f5295cd4258fe99f31e6320f4bd01c52c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "93ea3f1c47bbf57beb2553c566110cab3e2331f7f22195c1ee908de48f1f7e9a", "generation_seconds_batch": 22.288893957040273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.926278829574585, "target_z": 1.7187498750728454, "ce": 5.704906940460205, "genuineness": 4.632867813110352, "identity": 0.8734321594238281, "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_Concentration/ecf595fe2fedade6d5b1a73a34b9b97f5295cd4258fe99f31e6320f4bd01c52c.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "ed026f6fc8d847b0dce8f0d4532bc84460b96b53b5b5ece503c9e290937f14e9", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e17317f21607d8e325930f3b28d0f0842ff68164a6167e844987032a373903d2", "generation_seconds_batch": 23.784400914097205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0975091457366943, "target_z": 1.9531248839962134, "ce": 5.657250881195068, "genuineness": 4.356721878051758, "identity": 0.6640766859054565, "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_Concentration/ed026f6fc8d847b0dce8f0d4532bc84460b96b53b5b5ece503c9e290937f14e9.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": "ed05f7f1efbf877557642b3b1cdeb42817650e2ab8b983b806209d5edf2fa596", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "88c9a7a88f234517d65ad62b187bba52fdd4abee27a6f0847c646ef26f3d9b65", "generation_seconds_batch": 14.543022187892348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6682770252227783, "target_z": 2.734375131300989, "ce": 6.229123115539551, "genuineness": 4.231201171875, "identity": 0.5713428854942322, "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_Concentration/ed05f7f1efbf877557642b3b1cdeb42817650e2ab8b983b806209d5edf2fa596.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "eda3818ab5b1260f087ab52e9fb9deea165b9c51c0743cdd1689a9cf90d0ce42", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "6525a55b8721845fd1fa9670ddd203f2e8d41d9c4464f6540e4f2ae1de4207b0", "generation_seconds_batch": 17.7317154109478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9605250358581543, "target_z": 1.7656250726617124, "ce": 6.133810997009277, "genuineness": 4.68307638168335, "identity": 0.6621822118759155, "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_Concentration/eda3818ab5b1260f087ab52e9fb9deea165b9c51c0743cdd1689a9cf90d0ce42.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "ee1fe7b5a3c4b8214f029c1acca99389989327dc4b9e62cd02c4dbedb1b6357a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "b428504d64886b9b09fc8360ab95522e6840f80551fe55525df89a358fc46c51", "generation_seconds_batch": 23.648752513923682, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0518476963043213, "target_z": 1.8906248381046056, "ce": 6.117925643920898, "genuineness": 4.231201171875, "identity": 0.3889331817626953, "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_Concentration/ee1fe7b5a3c4b8214f029c1acca99389989327dc4b9e62cd02c4dbedb1b6357a.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "ee75cd615c75ccf217e5f39117f542c6adb7ddca45ad8e744453dd008ea55c9d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "4d2210eba4b37677fb6a0bb5e4e1e5666c8afca8fae2b3c235198b5c4c21462f", "generation_seconds_batch": 22.560504838009365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6180644035339355, "target_z": 1.2968750548149761, "ce": 5.847874641418457, "genuineness": 4.457139015197754, "identity": 0.5546565055847168, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/ee75cd615c75ccf217e5f39117f542c6adb7ddca45ad8e744453dd008ea55c9d.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "f076968818d5e820eb1220de4f96f1161a4dea34829291c9a24c1492325a6f25", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "e3e955684d55e8d4149aeb69b9ba30a5b86788c6c21aa6b894b122f7742dfbff", "generation_seconds_batch": 22.1251248230692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3144009113311768, "target_z": 2.2499999388111895, "ce": 5.601652145385742, "genuineness": 4.143336772918701, "identity": 0.5332828760147095, "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_Concentration/f076968818d5e820eb1220de4f96f1161a4dea34829291c9a24c1492325a6f25.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": "f0bf01fda4f21d85004da11e564547ed458bb15e6cae2966515fafc0e3213e91", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "63880c222bfd330a7cc4dfd83b4142be15d96236d7fa69d949ecc4875dd599d5", "generation_seconds_batch": 17.0996368030319, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.063263177871704, "target_z": 1.906250012747669, "ce": 6.1020402908325195, "genuineness": 4.394378662109375, "identity": 0.7638360261917114, "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_Concentration/f0bf01fda4f21d85004da11e564547ed458bb15e6cae2966515fafc0e3213e91.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "f0fcf54f245a6ab171d65a22b49246438ea19d6a07b158fece0d1b5ca15216b5", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "2f389f79d0cc5c2763f64bf7872e1207723e42edc8b974031bd3ec52fd4a4e4a", "generation_seconds_batch": 22.30927831400186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.029017210006714, "target_z": 1.8593751414991242, "ce": 5.808161735534668, "genuineness": 3.973883628845215, "identity": 0.6790773868560791, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/f0fcf54f245a6ab171d65a22b49246438ea19d6a07b158fece0d1b5ca15216b5.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "f1106490b2d3801e3c6da4bc430c4db441032385222ba26c983340524cd818b7", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "887b48f08dc584aac41c8de3b3c6634dfcd0a24790d57a1974f4da39ce0b669d", "generation_seconds_batch": 21.201404894934967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0975091457366943, "target_z": 1.9531248839962134, "ce": 5.093321323394775, "genuineness": 4.344170093536377, "identity": 0.5329233407974243, "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_Concentration/f1106490b2d3801e3c6da4bc430c4db441032385222ba26c983340524cd818b7.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": "f1465eac8b8e0a97efa152ab6d03ee895059b5efa3a1dff9983e673c6517d64c", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "9c41e7ba6ffbdcabe4a788ab2c250fdbf86c707c15e4657e7b3899a082a7a3ba", "generation_seconds_batch": 18.146255129016936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9205713272094727, "target_z": 1.7109376140916361, "ce": 5.7406487464904785, "genuineness": 4.557555198669434, "identity": 0.7159544229507446, "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_Concentration/f1465eac8b8e0a97efa152ab6d03ee895059b5efa3a1dff9983e673c6517d64c.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "f16fd3a2e2131a37999050438e4343b945869206031348883eb9457b0c3ca465", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "0bd166ff3088bc9e05bfd69516c948e1022b001643aeec54b877785b14026ad0", "generation_seconds_batch": 17.590600222931243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4125880002975464, "target_z": 1.015625011472902, "ce": 5.847874641418457, "genuineness": 4.337893962860107, "identity": 0.3178890347480774, "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_Concentration/f16fd3a2e2131a37999050438e4343b945869206031348883eb9457b0c3ca465.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "f182908ab192375b32ff423f9918d6fe179f40295ead3529bd2d57a9c96b2504", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c80ea4b017c3a3fdd1ee2814d3b59a1b04effd2780bd70acbbd77a9070f73e12", "generation_seconds_batch": 24.064566385000944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.211662769317627, "target_z": 2.109374998725233, "ce": 6.006728172302246, "genuineness": 4.344170093536377, "identity": 0.3822529911994934, "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_Concentration/f182908ab192375b32ff423f9918d6fe179f40295ead3529bd2d57a9c96b2504.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "f1f88782ffeead1995a3cc35e3ac6bc9c1aa509a9f2b84bb468219a683ce6e73", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "ffb373468f799c0c8810521b76de829698dfbb63b2be964e3e248dc3e72d465c", "generation_seconds_batch": 24.452369373990223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8121254444122314, "target_z": 1.562500086684148, "ce": 5.458683967590332, "genuineness": 4.406930446624756, "identity": 0.48298656940460205, "hypothesis": "La puerta sigue abierta. Te 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_Concentration/f1f88782ffeead1995a3cc35e3ac6bc9c1aa509a9f2b84bb468219a683ce6e73.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "3f25166e6d783b68bf1deeceedc5c2cc554495b806fd3b12af9548fb3dc08c85", "generation_seconds_batch": 18.23795158509165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6865565776824951, "target_z": 1.3906251236523879, "ce": 6.173524379730225, "genuineness": 4.68307638168335, "identity": 0.5737193822860718, "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_Concentration/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "f243aeeb953941c863573b3ad7b630fdbd98fa71567a2c32fb778813aa324c29", "bucket": "emo_Concentration", "phase": "wording", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "32247bfffbff7c848df17d4efc9e8b0fc46ba7b064d7ccaaaf95e8e5aa4a2163", "generation_seconds_batch": 17.518337804009207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0061864852905273, "target_z": 1.8281251185533203, "ce": 6.300607204437256, "genuineness": 4.300237655639648, "identity": 0.6521804332733154, "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_Concentration/f243aeeb953941c863573b3ad7b630fdbd98fa71567a2c32fb778813aa324c29.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "f2584994ab17f84a74d74bfc7b9fb3387f5bffbe4f52ed8a7b921097efe7cf4a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "0a072480f46304f1e5ff9ca71a6e08909c02ac9328913088e2955f0a83207d51", "generation_seconds_batch": 22.80388194601983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.074678421020508, "target_z": 1.9218748610504095, "ce": 6.221180438995361, "genuineness": 4.293961524963379, "identity": 0.39184466004371643, "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_Concentration/f2584994ab17f84a74d74bfc7b9fb3387f5bffbe4f52ed8a7b921097efe7cf4a.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": "f2677032ef867754badba2dd394de46294c5b0f5f586aa7f01774c1e770aa99c", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "06666b76243bab763e4fb2293f6cd234615e5d7c13c060cc6a64f8474a47d16d", "generation_seconds_batch": 17.966092425049283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2344934940338135, "target_z": 2.140625021671037, "ce": 5.617537498474121, "genuineness": 4.595211505889893, "identity": 0.689359724521637, "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_Concentration/f2677032ef867754badba2dd394de46294c5b0f5f586aa7f01774c1e770aa99c.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "f2e4204bae77d6a4720f9ddcbcfb3ff7455a8417694c66d913d10e9f315c8532", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "ee18f2a5323888d0515244dfbe41539606af92319bde4271256c40065f883373", "generation_seconds_batch": 23.722426072927192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8920328617095947, "target_z": 1.6718750038243007, "ce": 6.0146708488464355, "genuineness": 4.3881025314331055, "identity": 0.5778828859329224, "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_Concentration/f2e4204bae77d6a4720f9ddcbcfb3ff7455a8417694c66d913d10e9f315c8532.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": "f34f1d36669b3f3fd44d1c182120c6f8438299d1840b6f36966dfd55980689fe", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e4b7e5387f48d459588ff542f9c238728634746240fb819aa3f25b5b87c5c352", "generation_seconds_batch": 23.94703916599974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.926278829574585, "target_z": 1.7187498750728454, "ce": 6.141753673553467, "genuineness": 4.582659721374512, "identity": 0.8004337549209595, "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_Concentration/f34f1d36669b3f3fd44d1c182120c6f8438299d1840b6f36966dfd55980689fe.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "f3933994e3884145887056e4f590bde3bafbfb25f4b124e70bb3cdc0ca05ad3c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "63caf82ce62645cff887581bb409b769ef3fbe44a58397deca22b9975ea66b45", "generation_seconds_batch": 24.2953409019392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8406636714935303, "target_z": 1.6015623706111612, "ce": 6.070269584655762, "genuineness": 4.369274139404297, "identity": 0.7878053784370422, "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_Concentration/f3933994e3884145887056e4f590bde3bafbfb25f4b124e70bb3cdc0ca05ad3c.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": "f3aca8f4fd3ead2cd44d1589daedaf101e521bf4a18c3696c3dc730b184ec08a", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8ddffe39567460a28f5f23f21cc49490d1423f1f2b68c6677b3a66c607241306", "generation_seconds_batch": 16.784143800963648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2915701866149902, "target_z": 2.2187499158653856, "ce": 5.8875885009765625, "genuineness": 4.645420074462891, "identity": 0.7619749903678894, "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_Concentration/f3aca8f4fd3ead2cd44d1589daedaf101e521bf4a18c3696c3dc730b184ec08a.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "f42a4af4e05efd70ae20c633676c3ccb8f631b6a90aacde45bec456191b755a2", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "f795c5fc0a266a8d2f32b0263f8219dc807c6d5915d42a1562d46eb48044164d", "generation_seconds_batch": 21.248467418947257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9833557605743408, "target_z": 1.7968750956075163, "ce": 6.046441555023193, "genuineness": 4.243753433227539, "identity": 0.46311432123184204, "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_Concentration/f42a4af4e05efd70ae20c633676c3ccb8f631b6a90aacde45bec456191b755a2.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": "f45834facfe3e220de5095a8781d469addbd6b6f165df6f8f4254402cac0943b", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "f423e65e8fd8a58fa0b6b939824df66132ecd60604d9ec1db19a6f7c161d6f48", "generation_seconds_batch": 16.130910932086408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3372316360473633, "target_z": 2.2812499617569935, "ce": 5.772419452667236, "genuineness": 4.6705241203308105, "identity": 0.647476077079773, "hypothesis": "J'écris le numéro sur l'enveloppe. Lis-le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.09090909090909091, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Concentration/f45834facfe3e220de5095a8781d469addbd6b6f165df6f8f4254402cac0943b.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "f49e7a6749da4954fc387d9ae04582c97be2dd42f376510a924009f1eb97c22b", "bucket": "emo_Concentration", "phase": "wording", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "f6b0bed3076ca50b6fac6158c9bccb9d01fea496ae7c33a72a790aa1136de8c3", "generation_seconds_batch": 17.524757638922893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.017601728439331, "target_z": 1.843749966856061, "ce": 6.157639026641846, "genuineness": 4.494794845581055, "identity": 0.668867290019989, "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_Concentration/f49e7a6749da4954fc387d9ae04582c97be2dd42f376510a924009f1eb97c22b.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "f4a49109c059ee8b281fcf441a25662d4c576d60f75bfc6696bbad81fbfc2b4f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "8c79b43a9f669917dc14fc070286692f8f83d0a30041034376419eb2f21eeadf", "generation_seconds_batch": 18.04743400402367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8977406024932861, "target_z": 1.6796875911458322, "ce": 6.0305562019348145, "genuineness": 4.18099308013916, "identity": 0.6089377403259277, "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_Concentration/f4a49109c059ee8b281fcf441a25662d4c576d60f75bfc6696bbad81fbfc2b4f.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "f4ffe9ec782cfcf789e0956a2f7a54e1d53138cdf8b5acf6e5ce16c858adfe08", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "bbdf05b38f5d985a8ef32d59b3a60c6be7211220ea19e2ebebd154a872e9b3b2", "generation_seconds_batch": 24.130520625039935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0404324531555176, "target_z": 1.874999989801865, "ce": 6.340320587158203, "genuineness": 4.068024158477783, "identity": 0.6523905992507935, "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_Concentration/f4ffe9ec782cfcf789e0956a2f7a54e1d53138cdf8b5acf6e5ce16c858adfe08.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "f51262ba6d47d1f5353038743e60fb34c0d0036f409a86502e1940fbead3f433", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "76da1d0ab4a7b7f6341436ef9e4d967facc99ec8643be8db0e4c8bee4b7be89c", "generation_seconds_batch": 23.55825656093657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8749098777770996, "target_z": 1.6484375682000283, "ce": 6.1894097328186035, "genuineness": 4.632867813110352, "identity": 0.643383264541626, "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_Concentration/f51262ba6d47d1f5353038743e60fb34c0d0036f409a86502e1940fbead3f433.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "f52690a53864d901b756fd74e00bb46546b48c3450537a0fa504da09c1e09b27", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3aed7d896601a770c19f37284630f37b08488e891422f6408e8f06b3d4c8d8f1", "generation_seconds_batch": 24.19806946697645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.834956169128418, "target_z": 1.593750109629952, "ce": 6.133810997009277, "genuineness": 4.218649387359619, "identity": 0.2873428761959076, "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_Concentration/f52690a53864d901b756fd74e00bb46546b48c3450537a0fa504da09c1e09b27.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "f5821e624cb0c58905ca8ec2df9cd5a170d5467c6e92394ac560eadf233a767f", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "a52a78d61070ade74da5c10533eae7d6a7893676754186c9725592e98d635aff", "generation_seconds_batch": 18.027708064066246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.120339870452881, "target_z": 1.9843749069420173, "ce": 6.221180438995361, "genuineness": 4.268857479095459, "identity": 0.7701946496963501, "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_Concentration/f5821e624cb0c58905ca8ec2df9cd5a170d5467c6e92394ac560eadf233a767f.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "f63f3a642fd020cca21e504d0bca4848b49edb065b03e372610df405f4d97fa5", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "01bb9283ab2c69f9e32bb4e2411a886ae30db9a3748d306f52e311168b3c222a", "generation_seconds_batch": 24.653094066074118, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0404324531555176, "target_z": 1.874999989801865, "ce": 5.657250881195068, "genuineness": 4.532451152801514, "identity": 0.6067983508110046, "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_Concentration/f63f3a642fd020cca21e504d0bca4848b49edb065b03e372610df405f4d97fa5.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "f66c2f5116b5bb0d17c29d70665f1a7b794044a1a8411e462244cdb72bcbeac7", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "27b46108e74d06468447b1afa6f996c900b26f894bec6940f1df3d337a87ea8c", "generation_seconds_batch": 25.226080785039812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1146323680877686, "target_z": 1.9765626459608083, "ce": 6.062326908111572, "genuineness": 4.231201171875, "identity": 0.6262752413749695, "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_Concentration/f66c2f5116b5bb0d17c29d70665f1a7b794044a1a8411e462244cdb72bcbeac7.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "f6e523a2fce61cdf9bc9cd157f4b92a4e04761f3cdb7ff223e74f7291a8e9992", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4b86da7d10a1eb6ad97a30a6594acebe54f47c38527e22757f03c10946ca6c15", "generation_seconds_batch": 23.251021036994644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4924955368041992, "target_z": 1.1250000917832157, "ce": 6.260893821716309, "genuineness": 4.344170093536377, "identity": 0.6678768992424011, "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_Concentration/f6e523a2fce61cdf9bc9cd157f4b92a4e04761f3cdb7ff223e74f7291a8e9992.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "62b30bef828c8315be0fc28f4fd08a876bb2e0d275efff4b98041a627b6af8aa", "generation_seconds_batch": 17.816757199936546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0975091457366943, "target_z": 1.9531248839962134, "ce": 6.165581703186035, "genuineness": 4.582659721374512, "identity": 0.7869292497634888, "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_Concentration/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-1", "key": "f7a778b8b2443d1c87531cc61a8d3d277a79a06e541d8e25b4f7fc35dcd387a1", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78a59cf3b9741ddadca2e625cf469fc6c0bc334dd52f3bcb154269b48bbfca1b", "generation_seconds_batch": 23.743468948057853, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5267415046691895, "target_z": 1.1718749630317604, "ce": 6.006728172302246, "genuineness": 4.369274139404297, "identity": 0.43014436960220337, "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_Concentration/f7a778b8b2443d1c87531cc61a8d3d277a79a06e541d8e25b4f7fc35dcd387a1.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "f7fcf85526fdcb08fa95bd22256a6dbeb0a2ab0eb0b05b86c7bf8989c3ad98af", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "a819d838d774a0be458c9a04415fefe9f0af60f1cda867ef29bcca3c0c9f786c", "generation_seconds_batch": 22.26970523095224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0689709186553955, "target_z": 1.9140626000692005, "ce": 6.070269584655762, "genuineness": 4.331617832183838, "identity": 0.7249277830123901, "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_Concentration/f7fcf85526fdcb08fa95bd22256a6dbeb0a2ab0eb0b05b86c7bf8989c3ad98af.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_Concentration", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": "111c23d8e57f8a835e29db653152e1436b4ee9a0d5431b500461341488f7bdc8", "generation_seconds_batch": 17.494849067996256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2002475261688232, "target_z": 2.0937501504224922, "ce": 6.348263263702393, "genuineness": 4.381826400756836, "identity": 0.713042140007019, "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_Concentration/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-1", "key": "f93006cf9aebc5b29e3c5164e51bac69de5e3d867de82e99f75249035623ee35", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "f6a156434383b0b516821c299e12a335be388b9ff01d999c38fd2266dc50eb13", "generation_seconds_batch": 22.730919800000265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0518476963043213, "target_z": 1.8906248381046056, "ce": 5.6334228515625, "genuineness": 4.7081804275512695, "identity": 0.7190080881118774, "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_Concentration/f93006cf9aebc5b29e3c5164e51bac69de5e3d867de82e99f75249035623ee35.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "f9793924b0a0126c0b3df0abf6c5a66fff0e323fea5ff5070bbe82cb3482a6fd", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "41898ba0001fb1ce1d920fedfb27b7b5eb2687c3b2dd02b66732768c7176f32b", "generation_seconds_batch": 23.664943078067154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.029017210006714, "target_z": 1.8593751414991242, "ce": 6.09409761428833, "genuineness": 4.250029563903809, "identity": 0.6407767534255981, "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_Concentration/f9793924b0a0126c0b3df0abf6c5a66fff0e323fea5ff5070bbe82cb3482a6fd.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "f9d027fe713f9443db5f1f61e5f962825bd253ac8a43e3e1f347ee46248fd377", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "f14dfd30a7a482a9f1ef4e1aa398a06495dc379501eaf9359b9e09307b637077", "generation_seconds_batch": 23.635641342028975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1888320446014404, "target_z": 2.078124975779429, "ce": 6.157639026641846, "genuineness": 4.325342178344727, "identity": 0.664009153842926, "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_Concentration/f9d027fe713f9443db5f1f61e5f962825bd253ac8a43e3e1f347ee46248fd377.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "fa147760ddcc9f7b652c9996b66788a07e9b2aa6b8e895cff84646441e6c4728", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "12d8295086c23b459ce695d1bfce5fea61ee54b1eb569f72d14c56e4b99cc138", "generation_seconds_batch": 17.99058594298549, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8235406875610352, "target_z": 1.5781249349868889, "ce": 6.205295085906982, "genuineness": 4.042920112609863, "identity": 0.34524035453796387, "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_Concentration/fa147760ddcc9f7b652c9996b66788a07e9b2aa6b8e895cff84646441e6c4728.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": "fa186c4b8947a0a5afba0a3345373d4b40b62000d11be28cc9b5641b3233981a", "bucket": "emo_Concentration", "phase": "heldout", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f9e5a690c0c20ace6328a3ff239d224daa1be9b1dc87685d3c8863b381c08ed0", "generation_seconds_batch": 24.422744574956596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6180644035339355, "target_z": 1.2968750548149761, "ce": 6.157639026641846, "genuineness": 4.68307638168335, "identity": 0.7379676699638367, "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_Concentration/fa186c4b8947a0a5afba0a3345373d4b40b62000d11be28cc9b5641b3233981a.mp3" }, { "id": "emo_Concentration-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_Concentration-en-0", "key": "fb2eab89dcec832424e0f0fd7994eb73621c8bea70825ce83207f70fe5656f73", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] The door is still open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "041638e9e5077bb8793f472011e07c2d79109462982792c8b5cd436147964107", "generation_seconds_batch": 23.899630832951516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4468340873718262, "target_z": 1.0625000458916078, "ce": 6.173524379730225, "genuineness": 4.193545341491699, "identity": 0.23361003398895264, "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_Concentration/fb2eab89dcec832424e0f0fd7994eb73621c8bea70825ce83207f70fe5656f73.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "fb3e46e4705ecb221d87fa9b74fc99ad80ceeb1589438093ab2d444561d6a5cc", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "dbefaba48d1b14616ac94ead437e22e5f101236618a0ab712766a38a0438e32d", "generation_seconds_batch": 24.27551789500285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6637258529663086, "target_z": 1.359375100706584, "ce": 6.300607204437256, "genuineness": 4.356721878051758, "identity": 0.43169790506362915, "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_Concentration/fb3e46e4705ecb221d87fa9b74fc99ad80ceeb1589438093ab2d444561d6a5cc.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "fb494cabdc0ad2e1e3ee6f339f08d26f48ce1789492cf909412c994ae0b6bb5a", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "146f0fc350103fdab1a32f948c0156e1283265a706a40a6e00c7dec4a852b544", "generation_seconds_batch": 23.42651846096851, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5210338830947876, "target_z": 1.16406253888039, "ce": 6.054384231567383, "genuineness": 4.432034492492676, "identity": 0.21963414549827576, "hypothesis": "I found the little box. It was beside the old window. We can look inside", "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_Concentration/fb494cabdc0ad2e1e3ee6f339f08d26f48ce1789492cf909412c994ae0b6bb5a.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "fb99b4f8cc380ac8f5aa4172d204848d30232ba9c5e7f290429e80ae64c13a56", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "b4ccedd6ab8f7f4ec35f310a590eabe3834d63ba3eda0500441054dfac182fb5", "generation_seconds_batch": 18.272697194945067, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7208025455474854, "target_z": 1.4374999949009324, "ce": 6.24500846862793, "genuineness": 4.413206577301025, "identity": 0.3499715328216553, "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_Concentration/fb99b4f8cc380ac8f5aa4172d204848d30232ba9c5e7f290429e80ae64c13a56.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "fbf85411b29a89b590cc3a7b5a48c905cd98ebb3dae443be97a31335660745a3", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "04ce3ebb48f0e5847cb65ef1f88c4074420e08b21d61bc26d3a290d979857c54", "generation_seconds_batch": 16.05528374610003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9833557605743408, "target_z": 1.7968750956075163, "ce": 6.078212261199951, "genuineness": 4.595211505889893, "identity": 0.7458484172821045, "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_Concentration/fbf85411b29a89b590cc3a7b5a48c905cd98ebb3dae443be97a31335660745a3.mp3" }, { "id": "emo_Concentration-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_Concentration-de-0", "key": "fc52eaa86d9c09db83ad471c5797090580640a463fac33ce148c81d2effa6d0e", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "95ee3517f3b5b53779bcadd793777e7fd695d2a52423dadabef9f636b25f7c32", "generation_seconds_batch": 23.768282996024936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6751410961151123, "target_z": 1.3749999490093245, "ce": 6.252951145172119, "genuineness": 4.375550270080566, "identity": 0.6511449813842773, "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_Concentration/fc52eaa86d9c09db83ad471c5797090580640a463fac33ce148c81d2effa6d0e.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "fcb6952e9a15bf65de1a14fb95cc951cc5ee636a3029817066f9cfbe5ac896e1", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "49d00560d567c4d9891fd07d626b0ca4187657364e0379264a0c2de703e43bb3", "generation_seconds_batch": 24.130520625039935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.971940279006958, "target_z": 1.7812499209644532, "ce": 6.173524379730225, "genuineness": 4.3127899169921875, "identity": 0.5861935019493103, "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_Concentration/fcb6952e9a15bf65de1a14fb95cc951cc5ee636a3029817066f9cfbe5ac896e1.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "fcc29190b288692cc4e1b6e4174ab32c8d7dc89095f1a59a28b63ced96236061", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "031aafcf78807209cd5d29346249dce55787da01cad06c7cdcddbec5f499b310", "generation_seconds_batch": 23.66766610997729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6009414196014404, "target_z": 1.2734376191907038, "ce": 6.41180419921875, "genuineness": 4.3504462242126465, "identity": 0.2531224489212036, "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_Concentration/fcc29190b288692cc4e1b6e4174ab32c8d7dc89095f1a59a28b63ced96236061.mp3" }, { "id": "emo_Concentration-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_Concentration-fr-0", "key": "fcfb00c2a97a40a0ff742d00f181e16a22cc5cab45c3e46459992e27d0cf9643", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "56a614325a9e5afdf179f58b69f98a08405c3d421ac2456ce353a1faa420ccda", "generation_seconds_batch": 23.783317293971777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.074678421020508, "target_z": 1.9218748610504095, "ce": 5.704906940460205, "genuineness": 4.2751336097717285, "identity": 0.828048050403595, "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_Concentration/fcfb00c2a97a40a0ff742d00f181e16a22cc5cab45c3e46459992e27d0cf9643.mp3" }, { "id": "emo_Concentration-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_Concentration-es-1", "key": "fd7d1f5dc37b45ccdcd83f482dbf498b710150e8affaa084b12987eef92a913d", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "14c3a703ada5f8e71792055b879e1b043802cb8bbf9e442a2a592b93e5d32d71", "generation_seconds_batch": 22.40670905902516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2344934940338135, "target_z": 2.140625021671037, "ce": 6.09409761428833, "genuineness": 4.344170093536377, "identity": 0.718384325504303, "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_Concentration/fd7d1f5dc37b45ccdcd83f482dbf498b710150e8affaa084b12987eef92a913d.mp3" }, { "id": "emo_Concentration-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_Concentration-en-1", "key": "fe39c4f16078773ab33653358c285daa543a6ca341dd15da59a7ae9043734902", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] I found the little box.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4df8150c028109bb2c4d900d01d08348f605b3498081c20416fd2f157a3f19c6", "generation_seconds_batch": 23.445701073040254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6637258529663086, "target_z": 1.359375100706584, "ce": 6.284721851348877, "genuineness": 4.632867813110352, "identity": 0.43791162967681885, "hypothesis": "I f found the 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_Concentration/fe39c4f16078773ab33653358c285daa543a6ca341dd15da59a7ae9043734902.mp3" }, { "id": "emo_Concentration-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_Concentration-nl-0", "key": "fea3c9cd876b2f16d66d0719bf996bbf72a44541b899888bb2675c88df7406af", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] De deur staat nog open.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "6036164bf04e6ed81a81a30fbe6a4b12b3098835c6b445d4e47787f6b563fc58", "generation_seconds_batch": 22.13358556397725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.531292676925659, "target_z": 2.5468749936261657, "ce": 6.022613525390625, "genuineness": 4.256305694580078, "identity": 0.666739284992218, "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_Concentration/fea3c9cd876b2f16d66d0719bf996bbf72a44541b899888bb2675c88df7406af.mp3" }, { "id": "emo_Concentration-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_Concentration-es-0", "key": "ff4c8da9468331465ef2f2f43a25767ffee79eeeb74d6b39bfb815808cc8e593", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "9e6170e8a3db48daa4eab26610f4d150787987d19df378c76e71e44f31b4b7e3", "generation_seconds_batch": 23.65708191297017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9776480197906494, "target_z": 1.7890625082859848, "ce": 5.796247482299805, "genuineness": 4.557555198669434, "identity": 0.4848504662513733, "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_Concentration/ff4c8da9468331465ef2f2f43a25767ffee79eeeb74d6b39bfb815808cc8e593.mp3" }, { "id": "emo_Concentration-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_Concentration-de-1", "key": "ff65427a7199e4f218aa99e18499a19816fec17f8f5fc051468433682dfaab5c", "bucket": "emo_Concentration", "phase": "grid", "candidate": "manual-04d8f738e9e1", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a highly rhythmic and measured delivery, where each syllable is placed with the precision of a complex calculation.\nSCRIPT:\n(Begin with a very low, grounded vocal placement, establishing a sense of unshakeable mental foundation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain near-perfect, deliberate pacing throughout, using slight pauses between conceptual units for emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a brief, held vocal sustain on the final vowel, allowing the auditory impression of prolonged thought to linger.) [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": "766baa5913db1ae4622480984e517bd937380b8f2a2b8a7f970a1a911d8a488a", "generation_seconds_batch": 22.94649548199959, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8920328617095947, "target_z": 1.6718750038243007, "ce": 6.324435234069824, "genuineness": 4.557555198669434, "identity": 0.6895884871482849, "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_Concentration/ff65427a7199e4f218aa99e18499a19816fec17f8f5fc051468433682dfaab5c.mp3" }, { "key": "original-emo_Concentration-de-0-seed1701-scale0.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "f5975394191561b8e4c10380e0d864bc7aab0b9f7b4b7efab2715d6268a77ccc", "task_id": "emo_Concentration-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.498203158378601, "target_z": 1.132812515934586, "ce": 6.213237762451172, "genuineness": 4.68307638168335, "identity": 0.56557297706604, "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/audio/emo_Concentration/de/87dfb1851a603af482993858.mp3" }, { "key": "original-emo_Concentration-de-0-seed1701-scale0.5", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "6fd0bd78c274bf1bab0c0acf6f315a3d7b4403d3412cc50c956520433337b11c", "task_id": "emo_Concentration-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3926111459732056, "target_z": 0.9882812821878638, "ce": 6.260893821716309, "genuineness": 4.607763767242432, "identity": 0.6460604071617126, "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_Concentration/de/87e54137b241105e73913efa.mp3" }, { "key": "original-emo_Concentration-de-0-seed1701-scale0.75", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "fb0900dde47b2118a54b8f5c5ea5df2bd392d59a97f7ede465695f5b3a33685d", "task_id": "emo_Concentration-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.549572229385376, "target_z": 1.2031249859775643, "ce": 6.300607204437256, "genuineness": 4.482243061065674, "identity": 0.6158367395401001, "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_Concentration/de/599cd64067dc23f89181ccb1.mp3" }, { "key": "original-emo_Concentration-de-0-seed1701-scale1.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "1873c39df18397eec9ca73c22480fcde272e833349e6cff7273f5733c34c975c", "task_id": "emo_Concentration-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2641884088516235, "target_z": 0.8125000254953377, "ce": 6.173524379730225, "genuineness": 4.7332844734191895, "identity": 0.6080343723297119, "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_Concentration/de/9655fd4a998ac1cd85637f16.mp3" }, { "key": "original-emo_Concentration-de-0-seed1702-scale0.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "fef44b025686a2435bdd8b968a39eca96f4f8a36a36c46e9b611b266116ffcb4", "task_id": "emo_Concentration-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4125880002975464, "target_z": 1.015625011472902, "ce": 6.316492557525635, "genuineness": 4.770940780639648, "identity": 0.42864304780960083, "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_Concentration/de/1050b300b14101bdd7b1044a.mp3" }, { "key": "original-emo_Concentration-de-0-seed1702-scale0.5", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "55726d40c323d62dfc9d1686e6827f0ba8e9c29ef177162b4adf4cc257fa4a5f", "task_id": "emo_Concentration-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7493410110473633, "target_z": 1.476562605168268, "ce": 6.1894097328186035, "genuineness": 4.469690799713135, "identity": 0.6426839232444763, "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_Concentration/de/b7ede1e19ed1c9e624493966.mp3" }, { "key": "original-emo_Concentration-de-0-seed1702-scale0.75", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "64bab4e1988892fa201d1c9989caacbe2a031a2bc94cb260b45f7da2845d6d6d", "task_id": "emo_Concentration-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4696648120880127, "target_z": 1.0937500688374118, "ce": 6.062326908111572, "genuineness": 4.293961524963379, "identity": 0.44132310152053833, "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_Concentration/de/74b4fb31514a19b0159ef318.mp3" }, { "key": "original-emo_Concentration-de-0-seed1702-scale1.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "2ea998bc160f6cb57a4610a4fc1bc80696bcfd27d0f7cae808a345647ec83a11", "task_id": "emo_Concentration-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.715094804763794, "target_z": 1.4296874075794008, "ce": 6.221180438995361, "genuineness": 4.413206577301025, "identity": 0.3640747666358948, "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_Concentration/de/fa4aed9b6d3d7b153c1d89e3.mp3" }, { "key": "original-emo_Concentration-de-1-seed1701-scale0.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "3bfbc04524741f33d3c131334ab63fc7fc272c6dea2bc7d72ebfe17cb0cf83c4", "task_id": "emo_Concentration-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9376943111419678, "target_z": 1.7343750497159085, "ce": 6.356205940246582, "genuineness": 4.218649387359619, "identity": 0.5716452598571777, "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_Concentration/de/297d9c7b224c195f4160cc31.mp3" }, { "key": "original-emo_Concentration-de-1-seed1701-scale0.5", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "2bd1ece0d15c61da8d004ef6dc1846a929a7f7933e92de357e49fa503fb3e07f", "task_id": "emo_Concentration-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9434020519256592, "target_z": 1.74218763703744, "ce": 6.38003396987915, "genuineness": 4.369274139404297, "identity": 0.5184441208839417, "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_Concentration/de/eba0a4be9ccc8e5c3387d90c.mp3" }, { "key": "original-emo_Concentration-de-1-seed1701-scale0.75", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "cbf8f3280dc0ad9721fcf707956b7cb818336fe3db85496f3e56b5b919217421", "task_id": "emo_Concentration-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": 2.000478744506836, "target_z": 1.8203125312317887, "ce": 6.3641486167907715, "genuineness": 4.356721878051758, "identity": 0.5228663682937622, "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_Concentration/de/fd18e9000cc4a80ee66168b8.mp3" }, { "key": "original-emo_Concentration-de-1-seed1701-scale1.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "ae8b028611282003f2f0cfdb328573e115dc598e9f03d87ed93f855b7aaebb7f", "task_id": "emo_Concentration-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": 2.029017210006714, "target_z": 1.8593751414991242, "ce": 6.38003396987915, "genuineness": 4.444586753845215, "identity": 0.5981149673461914, "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_Concentration/de/53621a2a17bf9f44295b3954.mp3" }, { "key": "original-emo_Concentration-de-1-seed1702-scale0.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "071d79f987f946167c41e64beb566091cf628d94946e6f0a8bf091d55f2848e7", "task_id": "emo_Concentration-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9491095542907715, "target_z": 1.7499998980186493, "ce": 6.4515180587768555, "genuineness": 4.406930446624756, "identity": 0.5141165256500244, "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_Concentration/de/e4cb21a95f44b17ce539de65.mp3" }, { "key": "original-emo_Concentration-de-1-seed1702-scale0.5", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "fccd2e499fb0fd72795ce86a4a18f3a774f4cc66220d1a4e63c7e9d19e673b05", "task_id": "emo_Concentration-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7093873023986816, "target_z": 1.4218751465981918, "ce": 6.419747352600098, "genuineness": 4.356721878051758, "identity": 0.6220883131027222, "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_Concentration/de/80ee042de3c4eb84fdbd2f58.mp3" }, { "key": "original-emo_Concentration-de-1-seed1702-scale0.75", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "6149df8e3d539f2642e8ead8b8931f973666b5625cf88747b9106f335decc0bb", "task_id": "emo_Concentration-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.777879238128662, "target_z": 1.515624889095281, "ce": 6.395919322967529, "genuineness": 4.6203155517578125, "identity": 0.3754822015762329, "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_Concentration/de/25f24b70ee0f5043109185d3.mp3" }, { "key": "original-emo_Concentration-de-1-seed1702-scale1.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "24ca426ac369af7fec79ad13f289c4df9f12462dce88232fdb2f7f03b75ce489", "task_id": "emo_Concentration-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": 2.0860939025878906, "target_z": 1.9375000356934728, "ce": 6.300607204437256, "genuineness": 4.243753433227539, "identity": 0.555530309677124, "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_Concentration/de/0c4431e8e4018dfd0c97b1ff.mp3" }, { "key": "original-emo_Concentration-en-0-seed1701-scale0.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "f2b22a7444390a5fe6bd177d63f2ad8e38bd4814bf6aa5282ca717a26c964bf6", "task_id": "emo_Concentration-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.777879238128662, "target_z": 1.515624889095281, "ce": 6.268836498260498, "genuineness": 3.973883628845215, "identity": 0.2656324505805969, "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_Concentration/en/734748070a06c50d76a60790.mp3" }, { "key": "original-emo_Concentration-en-0-seed1701-scale0.5", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "5ab43fc314ce8f4c0a9393306d39686a29e70594733a31962f4af8435f973a90", "task_id": "emo_Concentration-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.292726755142212, "target_z": 0.8515624725925119, "ce": 6.221180438995361, "genuineness": 4.281409740447998, "identity": 0.29825448989868164, "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_Concentration/en/a8e266cd4349d8d9d2a43ac0.mp3" }, { "key": "original-emo_Concentration-en-0-seed1701-scale0.75", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "a436c9b6587974b1cea745b32e4bc5225116d7b396c013948b94c83345af04d3", "task_id": "emo_Concentration-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1757193803787231, "target_z": 0.6914062273728878, "ce": 6.24500846862793, "genuineness": 4.168440818786621, "identity": 0.2086045742034912, "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_Concentration/en/10e3afaab8e8316826510680.mp3" }, { "key": "original-emo_Concentration-en-0-seed1701-scale1.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "fcd5a64da81a7ebf264909b0048ff9cc3a64d707956e364a2663abf07339fa58", "task_id": "emo_Concentration-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6751410961151123, "target_z": 1.3749999490093245, "ce": 6.332377910614014, "genuineness": 4.137060642242432, "identity": 0.36017781496047974, "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_Concentration/en/194ae5e176cf54592316c76e.mp3" }, { "key": "original-emo_Concentration-en-0-seed1702-scale0.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "b4cc93ce3a04e44bd452e4b6bb73057e130c5ca4487915daed327edcb6633aea", "task_id": "emo_Concentration-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.595233678817749, "target_z": 1.2656250318691722, "ce": 6.157639026641846, "genuineness": 4.18099308013916, "identity": 0.18862807750701904, "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_Concentration/en/2af7646b4f15191931c97ea6.mp3" }, { "key": "original-emo_Concentration-en-0-seed1702-scale0.5", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "5b2580aea5c45b647dd71e2ccf0a1e21b1627601d2b1beb1aa9836fa0eb1e933", "task_id": "emo_Concentration-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5838183164596558, "target_z": 1.2500000203962702, "ce": 6.181467056274414, "genuineness": 4.030367851257324, "identity": 0.08635951578617096, "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_Concentration/en/415cdc58da4cd330abf62c69.mp3" }, { "key": "original-emo_Concentration-en-0-seed1702-scale0.75", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "0203c2572767dbd69dd442f46c28c3a38dc2d1df9d9498d1a986681176de3461", "task_id": "emo_Concentration-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6066489219665527, "target_z": 1.2812498801719128, "ce": 6.213237762451172, "genuineness": 3.9927117824554443, "identity": 0.17915621399879456, "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_Concentration/en/2aa0f35c0c57fd228e204920.mp3" }, { "key": "original-emo_Concentration-en-0-seed1702-scale1.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "f808606db334bc87d49da94fe287a9349aa29bb8cb7ae80c7dbfe774ca368f7b", "task_id": "emo_Concentration-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8121254444122314, "target_z": 1.562500086684148, "ce": 6.173524379730225, "genuineness": 4.055472373962402, "identity": 0.14735016226768494, "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_Concentration/en/f17f9ed13710053c105ec566.mp3" }, { "key": "original-emo_Concentration-en-1-seed1701-scale0.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "aa242c59ca9d5300be00acf2fe339ba1b4af550ad79b72e0741ba28247d90b24", "task_id": "emo_Concentration-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5838183164596558, "target_z": 1.2500000203962702, "ce": 6.38797664642334, "genuineness": 4.65797233581543, "identity": 0.4346206784248352, "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_Concentration/en/ba2b4d6c095b75f7d76a83ec.mp3" }, { "key": "original-emo_Concentration-en-1-seed1701-scale0.5", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "665a4ea0313b25fc624af3ba25c19ca4e26931af56be64cd56e8e432e8695c27", "task_id": "emo_Concentration-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7093873023986816, "target_z": 1.4218751465981918, "ce": 6.348263263702393, "genuineness": 4.457139015197754, "identity": 0.49248918890953064, "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_Concentration/en/8bf0ac451f197ab589b287b7.mp3" }, { "key": "original-emo_Concentration-en-1-seed1701-scale0.75", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "dbf2abc7f21a0d76c9585d27d018126ff3da1f3e43c2e9ca7ea193fe98068011", "task_id": "emo_Concentration-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5153262615203857, "target_z": 1.1562501147290196, "ce": 6.483288764953613, "genuineness": 4.6203155517578125, "identity": 0.459197461605072, "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_Concentration/en/cd3808448a2f1653a76f1786.mp3" }, { "key": "original-emo_Concentration-en-1-seed1701-scale1.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "c11a3c566e425b65d419a9da6de854d515ddddba38191d4b2be52ca188855cb0", "task_id": "emo_Concentration-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.292726755142212, "target_z": 0.8515624725925119, "ce": 6.292664527893066, "genuineness": 4.18726921081543, "identity": 0.3033924400806427, "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_Concentration/en/2e5709b5638faa036f28fe30.mp3" }, { "key": "original-emo_Concentration-en-1-seed1702-scale0.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "c075b1fb3b0cfea981b98bc921318df54ce3ed7c57f2374657f5df2a548d2740", "task_id": "emo_Concentration-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6294796466827393, "target_z": 1.3124999031177167, "ce": 6.372091293334961, "genuineness": 4.256305694580078, "identity": 0.4148819148540497, "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_Concentration/en/412a31b0b20ceb546db2e9e3.mp3" }, { "key": "original-emo_Concentration-en-1-seed1702-scale0.5", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "aea3fd6d7b47ac86cbe7fa38f7a580544c02049bcafbdffbef14500f6a06a79d", "task_id": "emo_Concentration-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3212652206420898, "target_z": 0.8906250828598475, "ce": 6.3641486167907715, "genuineness": 4.457139015197754, "identity": 0.2789296805858612, "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_Concentration/en/e3207318a15a722fdcb7e4cc.mp3" }, { "key": "original-emo_Concentration-en-1-seed1702-scale0.75", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "ab476d6b0818bcb93e6c088ac90fbbeb0056d4710764302033fb31f3abb6a608", "task_id": "emo_Concentration-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.549572229385376, "target_z": 1.2031249859775643, "ce": 6.356205940246582, "genuineness": 4.457139015197754, "identity": 0.41148632764816284, "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_Concentration/en/34981cf1e1d53c1538f6e527.mp3" }, { "key": "original-emo_Concentration-en-1-seed1702-scale1.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "432b5e3123fbc7307e119977a3dc0590d6ba6fdfbae5984197829f1414d1827c", "task_id": "emo_Concentration-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6351873874664307, "target_z": 1.3203124904392483, "ce": 6.316492557525635, "genuineness": 4.293961524963379, "identity": 0.44463467597961426, "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_Concentration/en/9949226678b76abbe1f8480e.mp3" }, { "key": "original-emo_Concentration-es-0-seed1701-scale0.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "fc7ee2e284db03823b65481e3327bb33a6b1bab2639213403b5fdd68f5965881", "task_id": "emo_Concentration-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1431705951690674, "target_z": 2.0156249298878213, "ce": 5.967014789581299, "genuineness": 4.168440818786621, "identity": 0.6361936330795288, "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_Concentration/es/77c4c98a78893455a5f27826.mp3" }, { "key": "original-emo_Concentration-es-0-seed1701-scale0.5", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "06da91906296c240b90d1972629222f42b65db767a21d0acd7a70482eca28ba1", "task_id": "emo_Concentration-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.120339870452881, "target_z": 1.9843749069420173, "ce": 6.173524379730225, "genuineness": 4.319066047668457, "identity": 0.4984956979751587, "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_Concentration/es/c3a4e1aa1ce9082c631cefb0.mp3" }, { "key": "original-emo_Concentration-es-0-seed1701-scale0.75", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "3963ee1ff4ec103dd2ff460fc90654d612036020b3797bab704449e753293ccd", "task_id": "emo_Concentration-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.120339870452881, "target_z": 1.9843749069420173, "ce": 5.998785495758057, "genuineness": 4.362998008728027, "identity": 0.6103041172027588, "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_Concentration/es/6ab9100d98e5ae5cd85615a4.mp3" }, { "key": "original-emo_Concentration-es-0-seed1701-scale1.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "5015a6c1926cfbe9dfc5bdd3a1d7f6f88611210c79d6dfba53f352ace8bc6aab", "task_id": "emo_Concentration-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8406636714935303, "target_z": 1.6015623706111612, "ce": 6.078212261199951, "genuineness": 4.3127899169921875, "identity": 0.5403980016708374, "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_Concentration/es/8df89ae7c465813187fad247.mp3" }, { "key": "original-emo_Concentration-es-0-seed1702-scale0.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "66a9cb9a66face8e0105d9be70e082956b3f62b6b0166164aa7edfff8c8589dc", "task_id": "emo_Concentration-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0233094692230225, "target_z": 1.8515625541775926, "ce": 5.935244083404541, "genuineness": 4.381826400756836, "identity": 0.5102676153182983, "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_Concentration/es/0d1c2b51ee7e9b4c5268339b.mp3" }, { "key": "original-emo_Concentration-es-0-seed1702-scale0.5", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "ee4efa9a58022fd577854e5cbf3d3df9e022b2807484c17dee90338c0ec499a2", "task_id": "emo_Concentration-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2002475261688232, "target_z": 2.0937501504224922, "ce": 6.022613525390625, "genuineness": 3.8922953605651855, "identity": 0.536878228187561, "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_Concentration/es/0ff3548dd0359f166c6739e9.mp3" }, { "key": "original-emo_Concentration-es-0-seed1702-scale0.75", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "335e9010183fd648bcf8234cde019445ede15b69045d3829d8076a1621f1867c", "task_id": "emo_Concentration-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6637258529663086, "target_z": 1.359375100706584, "ce": 6.070269584655762, "genuineness": 4.482243061065674, "identity": 0.598099946975708, "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_Concentration/es/486a3ee3cbb14975d18f95f7.mp3" }, { "key": "original-emo_Concentration-es-0-seed1702-scale1.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "94b379ad52bd0a81bb1dab2904f1b202ac231f8c21f6d26b19181e16390f5505", "task_id": "emo_Concentration-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2344934940338135, "target_z": 2.140625021671037, "ce": 5.863759994506836, "genuineness": 4.017816066741943, "identity": 0.6427960395812988, "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_Concentration/es/4c51bd90efdf298f3b04c074.mp3" }, { "key": "original-emo_Concentration-es-1-seed1701-scale0.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "25ec1cc1a8a92342c64b700a8c4aef2d252712e58ec02691c5a92158ab1e0e4a", "task_id": "emo_Concentration-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1317553520202637, "target_z": 2.0000000815850805, "ce": 5.990842819213867, "genuineness": 4.808597087860107, "identity": 0.6978359222412109, "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_Concentration/es/5e62660cac69b0396fc2441f.mp3" }, { "key": "original-emo_Concentration-es-1-seed1701-scale0.5", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "800ccdeb650e8ffe7fdc6f4405012331228d95836582edb166355e313a709d94", "task_id": "emo_Concentration-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.120339870452881, "target_z": 1.9843749069420173, "ce": 5.903473377227783, "genuineness": 4.444586753845215, "identity": 0.47249943017959595, "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_Concentration/es/59af56f506175ec0169dcc80.mp3" }, { "key": "original-emo_Concentration-es-1-seed1701-scale0.75", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "5b6766cb7eaacb19fc0b2c2fdfb7d6b947c018c0c5ff25fba9a7fc9d7449f25a", "task_id": "emo_Concentration-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.166001319885254, "target_z": 2.046874952833625, "ce": 6.109982967376709, "genuineness": 4.808597087860107, "identity": 0.5171942114830017, "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/audio/emo_Concentration/es/381b92eaf5f11d29450121f7.mp3" }, { "key": "original-emo_Concentration-es-1-seed1701-scale1.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "dfacb75da9c974efb8470367ed67554447f189a45d82661a627d67b26f9af2f2", "task_id": "emo_Concentration-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.120339870452881, "target_z": 1.9843749069420173, "ce": 6.022613525390625, "genuineness": 4.457139015197754, "identity": 0.5288983583450317, "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_Concentration/es/8b7fe6112ea92ce24dd040e6.mp3" }, { "key": "original-emo_Concentration-es-1-seed1702-scale0.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "0b4756a3a516374453d5da89413b622d541518a883f2e2999871091b2d1a3669", "task_id": "emo_Concentration-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.017601728439331, "target_z": 1.843749966856061, "ce": 6.09409761428833, "genuineness": 4.557555198669434, "identity": 0.7549468278884888, "hypothesis": "En Concrudro la cajita estaba 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/audio/emo_Concentration/es/a3e4627d27fee16b96f950b4.mp3" }, { "key": "original-emo_Concentration-es-1-seed1702-scale0.5", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "775bec25535922e806b2d4ca03a83a0b643a85d2b9fd467f90bdbee7d782dcf3", "task_id": "emo_Concentration-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8406636714935303, "target_z": 1.6015623706111612, "ce": 6.117925643920898, "genuineness": 4.7458367347717285, "identity": 0.6752114295959473, "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_Concentration/es/bb19b438848600bd8f5c49b5.mp3" }, { "key": "original-emo_Concentration-es-1-seed1702-scale0.75", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "2666b8e05369e518bf091408c5d239f364fcf8ecdb3e3a775ef3beb9e782ca2d", "task_id": "emo_Concentration-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2230780124664307, "target_z": 2.124999847027974, "ce": 6.0305562019348145, "genuineness": 4.7081804275512695, "identity": 0.656711995601654, "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_Concentration/es/bcc316a4216c7cde44c41d6a.mp3" }, { "key": "original-emo_Concentration-es-1-seed1702-scale1.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "c8d60eeeeeaa42f0d4612c8df59b6080ac6f0ca1a4b587571fbfa97b801fc96f", "task_id": "emo_Concentration-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0689709186553955, "target_z": 1.9140626000692005, "ce": 6.0305562019348145, "genuineness": 4.6203155517578125, "identity": 0.7554875016212463, "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_Concentration/es/bc0a6074fe5affc91133ac2e.mp3" }, { "key": "original-emo_Concentration-fr-0-seed1701-scale0.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "1664298cc46f820d951a3993aeb07e5c053c64be950c87c9135938842e34c7d1", "task_id": "emo_Concentration-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.777879238128662, "target_z": 1.515624889095281, "ce": 6.046441555023193, "genuineness": 4.457139015197754, "identity": 0.7409022450447083, "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_Concentration/fr/5071091096e4074cd61273ad.mp3" }, { "key": "original-emo_Concentration-fr-0-seed1701-scale0.5", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "087fb60cc01f785569de31f0491f515be6c49bbf91440f276237f9c3a792e373", "task_id": "emo_Concentration-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.954817295074463, "target_z": 1.7578124853401809, "ce": 6.125868320465088, "genuineness": 4.6956281661987305, "identity": 0.7444623708724976, "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/audio/emo_Concentration/fr/6228b0917aa492331595c2d4.mp3" }, { "key": "original-emo_Concentration-fr-0-seed1701-scale0.75", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "f4548916354eea307a1edfe3ad55fd743b0da2ecd00969cdb029b6cfee4c1cf4", "task_id": "emo_Concentration-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.834956169128418, "target_z": 1.593750109629952, "ce": 6.197352409362793, "genuineness": 4.507347106933594, "identity": 0.7631255984306335, "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_Concentration/fr/55b8e2622444cb5df23e9b3a.mp3" }, { "key": "original-emo_Concentration-fr-0-seed1701-scale1.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "ed1f57c970b3a4895f13cdc1ee5341c3545e45d189b0c876fde1bc6e530ba1a5", "task_id": "emo_Concentration-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0575554370880127, "target_z": 1.8984374254261371, "ce": 6.117925643920898, "genuineness": 4.3127899169921875, "identity": 0.6968063712120056, "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_Concentration/fr/f90d05e6bc68b9019948a9a9.mp3" }, { "key": "original-emo_Concentration-fr-0-seed1702-scale0.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "f66c845e56276cf4cf00bee37c32db69aafb04db27e0ee8700e81b55615fee1e", "task_id": "emo_Concentration-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8634943962097168, "target_z": 1.6328123935569652, "ce": 5.871703147888184, "genuineness": 4.482243061065674, "identity": 0.7847093343734741, "hypothesis": "La porte est encore vaupidée. 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/audio/emo_Concentration/fr/0830073c21bd161ea554c33d.mp3" }, { "key": "original-emo_Concentration-fr-0-seed1702-scale0.5", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "e6c7c71e63f20524fd4ae4a997fdbae339a59bf30d164abbd3307be7f508c2de", "task_id": "emo_Concentration-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.926278829574585, "target_z": 1.7187498750728454, "ce": 6.133810997009277, "genuineness": 4.545003414154053, "identity": 0.6590399742126465, "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_Concentration/fr/cb7f0965a8a6fcde1e55a10d.mp3" }, { "key": "original-emo_Concentration-fr-0-seed1702-scale0.75", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "9d7202c2697f738783e28ac535d1b2082c4b4c54e2e9022852a2f240f74a1dd3", "task_id": "emo_Concentration-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.789294719696045, "target_z": 1.5312500637383442, "ce": 6.006728172302246, "genuineness": 4.369274139404297, "identity": 0.6469499468803406, "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_Concentration/fr/e65fadf84e9d8fc365f3de7a.mp3" }, { "key": "original-emo_Concentration-fr-0-seed1702-scale1.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "42cd13c9d3d3032aa5d3e803b658d4b78eacfbee6ba1ccbb84dcd181acce5e35", "task_id": "emo_Concentration-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.926278829574585, "target_z": 1.7187498750728454, "ce": 6.23706579208374, "genuineness": 4.545003414154053, "identity": 0.6783120036125183, "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_Concentration/fr/b9b0c6a4f5984a0b0261ddf2.mp3" }, { "key": "original-emo_Concentration-fr-1-seed1701-scale0.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "537ce7a4088f6076cd0651c4ac4825a4111bbf92f06f86bbd0529b5456560a75", "task_id": "emo_Concentration-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7664639949798584, "target_z": 1.5000000407925402, "ce": 6.197352409362793, "genuineness": 4.7332844734191895, "identity": 0.7774941325187683, "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_Concentration/fr/b179be8e1f1d2c84f7dcddf6.mp3" }, { "key": "original-emo_Concentration-fr-1-seed1701-scale0.5", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "d69e6439e9b0107903aa86e0c042a8325713c650858a62bd196eebb5255a1362", "task_id": "emo_Concentration-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.029017210006714, "target_z": 1.8593751414991242, "ce": 6.141753673553467, "genuineness": 4.482243061065674, "identity": 0.7299849987030029, "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_Concentration/fr/7d919134ba93090b70490c54.mp3" }, { "key": "original-emo_Concentration-fr-1-seed1701-scale0.75", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "0e1adb72e0df55d6451f8fa012ce991080525a97f325d2ac4922df8966675615", "task_id": "emo_Concentration-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8463714122772217, "target_z": 1.6093749579326928, "ce": 6.117925643920898, "genuineness": 4.582659721374512, "identity": 0.8250432014465332, "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_Concentration/fr/16376150de9032415e7ca3e8.mp3" }, { "key": "original-emo_Concentration-fr-1-seed1701-scale1.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "3c9c92cfe13ef388916011b01ba197b26f42d928e1a8ef5b43b969cba1980cee", "task_id": "emo_Concentration-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0575554370880127, "target_z": 1.8984374254261371, "ce": 6.23706579208374, "genuineness": 4.545003414154053, "identity": 0.7515460848808289, "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_Concentration/fr/3592fd357d9b438a8dbb2930.mp3" }, { "key": "original-emo_Concentration-fr-1-seed1702-scale0.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "05987e34d9e6b9bc53673e8922b728ee4e6d70751feef33dda1eb68aaf026fad", "task_id": "emo_Concentration-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8406636714935303, "target_z": 1.6015623706111612, "ce": 6.229123115539551, "genuineness": 4.469690799713135, "identity": 0.807686448097229, "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_Concentration/fr/fe6d52d851eaa5ec232833dc.mp3" }, { "key": "original-emo_Concentration-fr-1-seed1702-scale0.5", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "582e1ed281e168dc95bc862bd88e4c3c8dbe8e321bb7c22d047a2eb20a48c326", "task_id": "emo_Concentration-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6123566627502441, "target_z": 1.2890624674934443, "ce": 6.24500846862793, "genuineness": 4.507347106933594, "identity": 0.6818238496780396, "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_Concentration/fr/ccb13abce4b3fa6ba95c734a.mp3" }, { "key": "original-emo_Concentration-fr-1-seed1702-scale0.75", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "b95a388b5252d9c7d87352e5cbfb68912086a7fd05be12a5c1e4e087e469c98c", "task_id": "emo_Concentration-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.789294719696045, "target_z": 1.5312500637383442, "ce": 6.181467056274414, "genuineness": 4.406930446624756, "identity": 0.7622954845428467, "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_Concentration/fr/910430d15861556d79d64857.mp3" }, { "key": "original-emo_Concentration-fr-1-seed1702-scale1.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "91481c876da4d6419f3f85af73932a3838c5d9b055bdae1cf2b2d422ba395ba9", "task_id": "emo_Concentration-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.880617618560791, "target_z": 1.6562501555215599, "ce": 6.157639026641846, "genuineness": 4.413206577301025, "identity": 0.7385342121124268, "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_Concentration/fr/6b295b36d781f99a9c6a4cbd.mp3" }, { "key": "original-emo_Concentration-nl-0-seed1701-scale0.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "e02d62f67051d54d531bc8e09500f9af9af4997c0b6d7232f854c846d70b0903", "task_id": "emo_Concentration-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1774168014526367, "target_z": 2.0625001274766883, "ce": 6.133810997009277, "genuineness": 4.344170093536377, "identity": 0.6394805312156677, "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_Concentration/nl/31b21541d16c4ebb0a05fe63.mp3" }, { "key": "original-emo_Concentration-nl-0-seed1701-scale0.5", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "66bf319a41449b95b5c3841b7b1f3ebaa2d20702373f2604798ee238b3f85704", "task_id": "emo_Concentration-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1888320446014404, "target_z": 2.078124975779429, "ce": 6.173524379730225, "genuineness": 4.356721878051758, "identity": 0.8301486968994141, "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_Concentration/nl/1aea7a7a4db84f674585126e.mp3" }, { "key": "original-emo_Concentration-nl-0-seed1701-scale0.75", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "a1cabfe53a6ad50f47b997ae7ed5dd3b6a46d7ef6b0392f558ed2e1861a85d37", "task_id": "emo_Concentration-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.451385259628296, "target_z": 2.437500076486013, "ce": 5.927301406860352, "genuineness": 4.149612903594971, "identity": 0.6641548871994019, "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_Concentration/nl/3b36da7a9b8e1c958afd40c4.mp3" }, { "key": "original-emo_Concentration-nl-0-seed1701-scale1.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "99ea0f747fd58752f46453cb55b2a99776d60313a24aa4bfaaf8ef697b2b0ba0", "task_id": "emo_Concentration-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4628005027770996, "target_z": 2.453124924788754, "ce": 6.078212261199951, "genuineness": 4.243753433227539, "identity": 0.5883939862251282, "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_Concentration/nl/986ee35677c50bd27d359345.mp3" }, { "key": "original-emo_Concentration-nl-0-seed1702-scale0.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "d9d7155a58c3098a097257e215856bcd94c8ca2e957c9e77162e36ddfbd06270", "task_id": "emo_Concentration-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.108924627304077, "target_z": 1.9687500586392768, "ce": 6.141753673553467, "genuineness": 4.262581825256348, "identity": 0.743532121181488, "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_Concentration/nl/bff8d4c1bec09b8b191471c6.mp3" }, { "key": "original-emo_Concentration-nl-0-seed1702-scale0.5", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "7cc2251643dd6a9ee0b364c6995f7a531fd7abed4d64fff808a43d7041f5df26", "task_id": "emo_Concentration-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.091801643371582, "target_z": 1.9453126230150044, "ce": 6.141753673553467, "genuineness": 4.482243061065674, "identity": 0.6394829750061035, "hypothesis": "De deur staan 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/audio/emo_Concentration/nl/77f91cbd7ec5f86ee757ad09.mp3" }, { "key": "original-emo_Concentration-nl-0-seed1702-scale0.75", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "e8c37929e832f064e659d94219d7b2c98c7c3fc02ab3f0c8fca738f5746a5308", "task_id": "emo_Concentration-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3828930854797363, "target_z": 2.3437500076486013, "ce": 6.133810997009277, "genuineness": 4.457139015197754, "identity": 0.7315230369567871, "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_Concentration/nl/25ba91bd9a0649ea9358b3a2.mp3" }, { "key": "original-emo_Concentration-nl-0-seed1702-scale1.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "947dc721d7637003b025bbb06390b079b76c87e7b6b2f350ff674f900e04039e", "task_id": "emo_Concentration-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.39430832862854, "target_z": 2.359374855951342, "ce": 6.1894097328186035, "genuineness": 4.356721878051758, "identity": 0.7338560819625854, "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_Concentration/nl/8dde8df776c7af288f02d51d.mp3" }, { "key": "original-emo_Concentration-nl-1-seed1701-scale0.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "07cc20b5e2767b09ed65c63ddb9941bd87bd2924368c2e687cb1b6d5179f7479", "task_id": "emo_Concentration-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": 2.1431705951690674, "target_z": 2.0156249298878213, "ce": 6.054384231567383, "genuineness": 4.457139015197754, "identity": 0.27738264203071594, "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_Concentration/nl/68f959e2be5aa85173284de2.mp3" }, { "key": "original-emo_Concentration-nl-1-seed1701-scale0.5", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "cc1373d0fac2bc7cb4cfc749bcb39ce17e9bbe53eca22b147b0e3e2ca97533ff", "task_id": "emo_Concentration-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": 2.120339870452881, "target_z": 1.9843749069420173, "ce": 6.133810997009277, "genuineness": 4.331617832183838, "identity": 0.7294557094573975, "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_Concentration/nl/6eda23c3ab25d1d44c77bb98.mp3" }, { "key": "original-emo_Concentration-nl-1-seed1701-scale0.75", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "0079ccec5ac8ad398c158fcef12af9311bcd6dcd0f64ee2cf2ca09a4a3ffa8a5", "task_id": "emo_Concentration-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": 2.5198774337768555, "target_z": 2.531250145323425, "ce": 5.982900142669678, "genuineness": 4.400654315948486, "identity": 0.5257325172424316, "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_Concentration/nl/b9d4fd2f584311147da42446.mp3" }, { "key": "original-emo_Concentration-nl-1-seed1701-scale1.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "60864945803ada517db88c43b0ca8a020cc71259b2f89cb95da2621f585869ca", "task_id": "emo_Concentration-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.777879238128662, "target_z": 1.515624889095281, "ce": 6.1894097328186035, "genuineness": 4.356721878051758, "identity": 0.4858993887901306, "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_Concentration/nl/17da371121fb728f708c59f5.mp3" }, { "key": "original-emo_Concentration-nl-1-seed1702-scale0.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "e44dce891e67d85f87d0aeb1699b5bc2a33a9fdd817262fe3ff457fa69a67cfd", "task_id": "emo_Concentration-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9091558456420898, "target_z": 1.695312439448573, "ce": 6.205295085906982, "genuineness": 4.406930446624756, "identity": 0.7632379531860352, "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_Concentration/nl/d42096aa486b0e6520175ddc.mp3" }, { "key": "original-emo_Concentration-nl-1-seed1702-scale0.5", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "9b5a0f91a32d42fd746e8fa7f1a522e3afc7ff13260b5561c5cc3188dd88886e", "task_id": "emo_Concentration-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9319865703582764, "target_z": 1.726562462394377, "ce": 6.086154937744141, "genuineness": 4.319066047668457, "identity": 0.630341649055481, "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_Concentration/nl/0e0c013b2af5e99b87bb6a3c.mp3" }, { "key": "original-emo_Concentration-nl-1-seed1702-scale0.75", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "2b1988ea5a5af32d750d5a8c7b6b92c0ac139b0443e6a8885a24eb881041e276", "task_id": "emo_Concentration-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9833557605743408, "target_z": 1.7968750956075163, "ce": 6.078212261199951, "genuineness": 4.369274139404297, "identity": 0.7015279531478882, "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_Concentration/nl/8657180f98de91a338e49cfd.mp3" }, { "key": "original-emo_Concentration-nl-1-seed1702-scale1.0", "bucket": "emo_Concentration", "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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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 Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Concentration. 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": "b31e6ff6b1368fb289aaa4c8972bd64390c9fdb0f74db375a07c8835f28a3ca1", "mp3_sha256": "4174d8a8992ced204eec0bed42e6fe66b8ca38a17937f9c4f9f094093cce0d12", "task_id": "emo_Concentration-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Concentration. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Concentration. 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 Concentration. 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 Concentration. 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": 2.4285545349121094, "target_z": 2.406250053540209, "ce": 5.8875885009765625, "genuineness": 4.1998209953308105, "identity": 0.5003135204315186, "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_Concentration/nl/2e703875ed6bf68e5ac26162.mp3" } ], "source_standard_audio_unchanged": true }