{ "complete": true, "report": { "bucket": "emo_Contentment", "label": "Intense Contentment", "definition": { "id": "emo_Contentment", "category": "emotion", "head": "emo_Contentment", "pole": "high", "label": "Intense Contentment", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_contentment/full-v2-sealed/sealed-selected", "mission": "emotion_contentment", "format_status": "CANONICAL", "heldout": true, "qualified": true, "source_cfg": 3, "source_model": { "label": "Humaneness 1.5 + real-speech rank 4", "repo": "laion/Humaneness-Voice-Large-1.5-RealSpeech-LoRAs", "revision": "fed33e554f094fcdc89fc0124aed2f9d42018714", "rank": 4 }, "metrics": { "ce": 6.390875563621521, "genuineness": 4.258125574588775, "wer": 0.007412474766201128, "identity": 0.5484130078554154, "voiceclap": -0.16611749531701206, "fitness": 0.8293164705761656, "steering_v2": 0.9965378328412083, "raw_target": 1.9715647554397584, "target_cdf": 0.9965378328412083, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.415617008209228, "genuineness": 4.250280513763427, "wer": 0.00849758991472006, "identity": 0.5484130078554154, "fitness": 0.8286291837455224, "steering_v2": 0.9963225448954101 }, "none": { "n": 50, "ce": 6.366134119033814, "genuineness": 4.265970635414123, "wer": 0.006327359617682198, "identity": null, "fitness": 0.8300037574068089, "steering_v2": 0.9967531207870065 } } } } ], "selected_wording": { "id": "manual-e34e2073bf7b", "general": "Treat the delivery as a shared, comfortable secret; intimate, low-key, and deeply resonant.", "inline": [ "Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.", "Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.", "Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo." ], "cfg": 3, "recipe": "P09", "strategy": "local-Gemma-mutation", "timing_syntax": "canonical", "canonical_labels": true, "neutral_event": "keep", "parent": "cfg-3", "origin": "exact_frozen_manual_recipe" }, "selection": { "manual_no_adapter": { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 4.040624971532135, "target_raw": 2.389962410926819, "ce": 6.19933807849884, "genuineness": 4.2547364950180055, "identity": 0.5345435991883278, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.016321256756782532, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 4.120312468019866, "target_raw": 2.4301096916198732, "ce": 6.19179253578186, "genuineness": 4.235280752182007, "identity": 0.5476366072893143, "wer": 0.05333333333333333, "valid_fraction": 0.9, "identity_delta": -0.003228248655796051, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 4.040624971532135, "target_raw": 2.389962410926819, "ce": 6.19933807849884, "genuineness": 4.2547364950180055, "identity": 0.5345435991883278, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.016321256756782532, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 4.018749962289322, "target_raw": 2.3789415836334227, "ce": 6.1631989002227785, "genuineness": 4.221787285804749, "identity": 0.5507984198629856, "wer": 0.006458333333333333, "valid_fraction": 1, "identity_delta": -6.643608212471008e-05, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": 3.9062499755989726, "target_raw": 2.322263073921204, "ce": 6.235477256774902, "genuineness": 4.225239109992981, "identity": 0.5182822659611702, "wer": 0.0029411764705882353, "valid_fraction": 1, "identity_delta": -0.032582589983940126, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": 3.825781196668967, "target_raw": 2.2817221760749815, "ce": 6.230314493179321, "genuineness": 4.306513881683349, "identity": 0.5761862307786941, "wer": 0.0058823529411764705, "valid_fraction": 1, "identity_delta": 0.02532137483358383, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": 3.7101561630251263, "target_raw": 2.223469239473343, "ce": 6.2219746828079225, "genuineness": 4.257874512672425, "identity": 0.5122924715280532, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.038572384417057036, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": 3.5687500036971254, "target_raw": 2.1522275388240812, "ce": 6.189409685134888, "genuineness": 4.256619286537171, "identity": 0.5675855994224548, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.016720743477344514, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": 3.5367187131211746, "target_raw": 2.1360898852348327, "ce": 6.218797636032105, "genuineness": 4.319379687309265, "identity": 0.5440847381949425, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.006780117750167847, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": 3.4265625619268496, "target_raw": 2.0805922210216523, "ce": 6.225946021080017, "genuineness": 4.331617999076843, "identity": 0.5457824483513832, "wer": 0.005555555555555555, "valid_fraction": 1, "identity_delta": -0.0050824075937271115, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 4.120312468019866, "target_raw": 2.4301096916198732, "ce": 6.19179253578186, "genuineness": 4.235280752182007, "identity": 0.5476366072893143, "wer": 0.05333333333333333, "valid_fraction": 0.9, "identity_delta": -0.003228248655796051, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 4.011718704248074, "target_raw": 2.375399172306061, "ce": 6.1566462278366085, "genuineness": 4.227435684204101, "identity": 0.5264224603772163, "wer": 0.00625, "valid_fraction": 1, "identity_delta": -0.02444239556789398, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 4.005468787803107, "target_raw": 2.372250407934189, "ce": 6.1850412607192995, "genuineness": 4.175030779838562, "identity": 0.5463347092270852, "wer": 0.00625, "valid_fraction": 1, "identity_delta": -0.0045301467180252075, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 3.966406215524306, "target_raw": 2.3525703310966493, "ce": 6.209266471862793, "genuineness": 4.212686991691589, "identity": 0.5348442241549491, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.01602063179016113, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": 3.9585937815179935, "target_raw": 2.3486343562602996, "ce": 6.202912282943726, "genuineness": 4.2362221598625185, "identity": 0.5839919596910477, "wer": 0.008596491228070175, "valid_fraction": 1, "identity_delta": 0.033127103745937345, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": 3.904687446206826, "target_raw": 2.3214758574962615, "ce": 6.218797612190246, "genuineness": 4.276074981689453, "identity": 0.5389467991888524, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.01191805675625801, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 3.853906276157162, "target_raw": 2.2958918452262878, "ce": 6.234285855293274, "genuineness": 4.23904641866684, "identity": 0.552381619811058, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.0015167638659477234, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": 3.8359375016637065, "target_raw": 2.2868390142917634, "ce": 6.228328824043274, "genuineness": 4.216766440868378, "identity": 0.5465431414544583, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.004321714490652084, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": 3.7781249670955845, "target_raw": 2.257712537050247, "ce": 6.203309416770935, "genuineness": 4.280154418945313, "identity": 0.5323870986700058, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.018477757275104523, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": 3.7398437482438656, "target_raw": 2.238426113128662, "ce": 6.233888697624207, "genuineness": 4.24469485282898, "identity": 0.5154072545468807, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.0354576013982296, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": 3.6972656179292476, "target_raw": 2.2169748663902284, "ce": 6.241434216499329, "genuineness": 4.2531674861907955, "identity": 0.5123946964740753, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.038470159471035006, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": 3.6914062717206115, "target_raw": 2.2140228748321533, "ce": 6.230711603164673, "genuineness": 4.270112788677215, "identity": 0.5726798251271248, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.021814969182014466, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": 3.6863281724618466, "target_raw": 2.2114644825458525, "ce": 6.199735188484192, "genuineness": 4.2377912402153015, "identity": 0.5165177460759878, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.034347109869122504, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 3.6548828023097983, "target_raw": 2.195622020959854, "ce": 6.229917359352112, "genuineness": 4.230887591838837, "identity": 0.5646594397723674, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.013794583827257156, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": 3.642968736043352, "target_raw": 2.1896196067333222, "ce": 6.219591903686523, "genuineness": 4.34260106086731, "identity": 0.5690312556922436, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.018166399747133254, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": 3.6242187855848313, "target_raw": 2.18017321228981, "ce": 6.204500794410706, "genuineness": 4.307769060134888, "identity": 0.5935925602912903, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": 0.042727704346179965, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": 3.617968739001052, "target_raw": 2.177024382352829, "ce": 6.212046337127686, "genuineness": 4.304317212104797, "identity": 0.5754138037562371, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.02454894781112671, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": 3.6121093573000125, "target_raw": 2.1740723729133604, "ce": 6.238257193565369, "genuineness": 4.302120637893677, "identity": 0.5499034278094769, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.0009614281356334686, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": 3.6082031343814553, "target_raw": 2.1721043825149535, "ce": 6.220783257484436, "genuineness": 4.332245612144471, "identity": 0.5579893037676811, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0071244478225708004, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": 3.608203098889052, "target_raw": 2.1721043646335603, "ce": 6.247391247749329, "genuineness": 4.327224719524383, "identity": 0.5323514230549335, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.018513432890176772, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": 3.5417968478723427, "target_raw": 2.1386482954025268, "ce": 6.245802712440491, "genuineness": 4.311220860481262, "identity": 0.5447480387985706, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.0061168171465396885, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": 3.5175780859491135, "target_raw": 2.1264466643333435, "ce": 6.198940968513488, "genuineness": 4.293647968769074, "identity": 0.5673389121890068, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.016474056243896484, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": 3.460156228094532, "target_raw": 2.0975170135498047, "ce": 6.202117967605591, "genuineness": 4.270112800598144, "identity": 0.5336714811623097, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.017193374782800676, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 4.017187492051181, "target_raw": 2.3781543970108032, "ce": 6.19973521232605, "genuineness": 4.143650674819947, "identity": 0.4708820626139641, "wer": 0.049999999999999996, "valid_fraction": 0.95, "identity_delta": -0.07998279333114625, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": 3.1953124768929664, "target_raw": 1.964086338877678, "ce": 6.207677817344665, "genuineness": 4.275447416305542, "identity": 0.5508648559451104, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.5, "n": 20, "target_z": 3.1068359315152785, "target_raw": 1.9195110559463502, "ce": 6.15565333366394, "genuineness": 4.359860181808472, "identity": 0.5660799711942672, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.015215115249156952, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": 2.99140625988981, "target_raw": 1.861356544494629, "ce": 6.173127245903015, "genuineness": 4.386219465732575, "identity": 0.5552921667695045, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.004427310824394226, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": 3.0031250232918896, "target_raw": 1.8672605633735657, "ce": 6.131428217887878, "genuineness": 4.299296355247497, "identity": 0.5974542230367661, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.04658936709165573, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": 3.113105472893091, "target_raw": 1.9226697075366974, "ce": 6.256922426223755, "genuineness": 4.337642979621887, "identity": 0.5603747323155404, "wer": 0.007623376623376623, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": 3.859375026101705, "target_raw": 2.298647050857544, "ce": 6.275826005935669, "genuineness": 4.28981954574585, "identity": 0.5565548980236054, "wer": 0.031592885375494074, "valid_fraction": 0.96, "identity_delta": -0.003819834291934967, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": 3.8793750190032243, "target_raw": 2.3087232279777528, "ce": 6.253109979629516, "genuineness": 4.206097207069397, "identity": 0.5051676166057587, "wer": 0.01761154368133773, "valid_fraction": 1, "identity_delta": -0.055207115709781644, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": 3.868437495452536, "target_raw": 2.3032128047943115, "ce": 6.281227035522461, "genuineness": 4.220783095359803, "identity": 0.5457810742408037, "wer": 0.008365800865800865, "valid_fraction": 1, "identity_delta": -0.014593658074736594, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": 0.010937523550688385, "ci95_z": [ -0.05968745626300729, 0.09624999334517437 ], "language_deltas": { "en": -0.05937500480626299, "de": 0.05312502920729027, "fr": -0.07812488427997692, "nl": -0.023437503142556614, "es": 0.16249998077494818 }, "languages_improved": 2, "clear_gain": false, "delta_ce": -0.028117055892944335, "delta_genuineness": -0.014685888290405274, "delta_wer": 0.009245742815536865, "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": 0.019999992901519263, "ci95_z": [ -0.019687522515493418, 0.06874996347240159 ], "language_deltas": { "en": -0.01718759852839029, "de": 0.1031249759686852, "fr": -0.010937386313395959, "nl": 0.05156248798434264, "es": -0.02656251460364527 }, "languages_improved": 2, "clear_gain": false, "delta_ce": -0.022716026306152343, "delta_genuineness": -0.08372233867645264, "delta_wer": -0.01398134169415634, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 0.7462695532086139, "ci95_z": [ 0.5831250516858122, 0.918496075664125 ], "language_deltas": { "en": 0.7156251401210504, "de": 0.4921875423320852, "fr": 1.0344726473653456, "nl": 0.6078125168219202, "es": 0.8812499194026677 }, "languages_improved": 5, "clear_gain": true, "delta_ce": 0.018903579711914063, "delta_genuineness": -0.047823433876037595, "delta_wer": 0.02396950875211745, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 4.0, "reason": "Use manual-only configuration; no clear qualifying incremental adapter gain" }, "reference_only": true, "updated": 1793023762.3334954, "example": { "text": "Alguien ha movido la pequeña silla azul. Estaba aquí... junto a la estantería alta. La colocaremos después de comer.", "sentences": [ "Alguien ha movido la pequeña silla azul.", "Estaba aquí... junto a la estantería alta.", "La colocaremos después de comer." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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.", "language": "es", "seed": 1702, "scale": 0.0, "cfg": 4.0, "frames": 128, "reference": true } }, "rows": [ { "id": "emo_Contentment-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_Contentment-en-1", "key": "005370e386cb8c772af97b5b33ef7fc81fbd598954b2ba03e954e1498e726f54", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ef40268c319854a2e7e6855a967ed3163fdc2f4f7a6f854d915b613e09ea7e4a", "generation_seconds_batch": 24.23914376902394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6056556701660156, "target_z": 4.468750003697125, "ce": 6.284721851348877, "genuineness": 4.193545341491699, "identity": 0.2387300580739975, "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_Contentment/005370e386cb8c772af97b5b33ef7fc81fbd598954b2ba03e954e1498e726f54.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "00561a187331da22366f7c56ce66f712b8237094a9b372487a39fdaa9559c52f", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "816447a634bb83ce281d2f5ba926ec9c388315a7142cc43050b317a4fd0c54ba", "generation_seconds_batch": 21.284363360027783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9205362796783447, "target_z": 5.093749929754619, "ce": 6.062326908111572, "genuineness": 4.174716949462891, "identity": 0.5721376538276672, "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_Contentment/00561a187331da22366f7c56ce66f712b8237094a9b372487a39fdaa9559c52f.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "005ae8945055da4fd9f341a3f567f6480a08dc3ab22f2ab1dc38bf0419f69800", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "912dea31b0274be3dbc27f58b1a60ab0f36081f0400e7218515de40d5654637a", "generation_seconds_batch": 21.610677831922658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.141206741333008, "target_z": 3.5468750536083173, "ce": 5.982900142669678, "genuineness": 3.9927117824554443, "identity": 0.45957231521606445, "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_Contentment/005ae8945055da4fd9f341a3f567f6480a08dc3ab22f2ab1dc38bf0419f69800.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "005c3509719a4d33dca75f79f8de80f10e797f93824235b7383a62e87edd7a8a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "7a45bb8707aeb9d990658564d4f619b142a9fe19ba89d5f068b8015e95ec8ec8", "generation_seconds_batch": 20.47220836696215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0861027240753174, "target_z": 3.4375002440102724, "ce": 6.1894097328186035, "genuineness": 4.68307638168335, "identity": 0.584678590297699, "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_Contentment/005c3509719a4d33dca75f79f8de80f10e797f93824235b7383a62e87edd7a8a.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": "008f52c170f3ea38014e86a64f78a71432577ffc3a7d73c51f5a6525218520de", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2fb9a2d0c5979b30059fee276a63d4ef9819f6592517afa785c9e063a1d13983", "generation_seconds_batch": 15.2186626449693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0703585147857666, "target_z": 3.4062498927833653, "ce": 6.340320587158203, "genuineness": 4.1998209953308105, "identity": 0.5811207890510559, "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_Contentment/008f52c170f3ea38014e86a64f78a71432577ffc3a7d73c51f5a6525218520de.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "010159afe9d5e40fde824a56885cdae859d41c67a5f51d7d2d51a1a11cce79f4", "bucket": "emo_Contentment", "phase": "wording", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f2142bbe368436840599cd230138f94d74e7023057b5dbaae61aaf41d90dbbc1", "generation_seconds_batch": 15.689225109061226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7712218761444092, "target_z": 2.812499844720736, "ce": 6.062326908111572, "genuineness": 4.457139015197754, "identity": 0.7715305089950562, "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_Contentment/010159afe9d5e40fde824a56885cdae859d41c67a5f51d7d2d51a1a11cce79f4.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "0126c8170c2d48d1ab7a9d2954026fbfa04cdc682864aaa2135b9d632b820ff5", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "988a0986c358207a991467c6f78030d8bd42ee64486442b7587ad3f2d6afd375", "generation_seconds_batch": 21.7692374039907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6686317920684814, "target_z": 4.593749988908624, "ce": 6.0146708488464355, "genuineness": 4.024092197418213, "identity": 0.547386884689331, "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_Contentment/0126c8170c2d48d1ab7a9d2954026fbfa04cdc682864aaa2135b9d632b820ff5.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "01386dd6cddcc3c4b16585313e7d39504a5cdb5b713e28fdd6425479e96d24df", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "1ccc7c6d42687a4e58d6ab5ffce264513ef17c80fa664d0424603d90fa6d7342", "generation_seconds_batch": 21.561780423042364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1805667877197266, "target_z": 3.6249999852114985, "ce": 6.38797664642334, "genuineness": 4.331617832183838, "identity": 0.4331163167953491, "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_Contentment/01386dd6cddcc3c4b16585313e7d39504a5cdb5b713e28fdd6425479e96d24df.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "0145760282cfb9fef425be8c3f747b7909e908904b98efd058060931ec2604f7", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f3f65582c3967663fdfeb9ec5f2759abf20929eb8c3f5949b4edbc5ff8de3e37", "generation_seconds_batch": 20.130340456031263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5508054494857788, "target_z": 2.3749998964804906, "ce": 6.109982967376709, "genuineness": 4.381826400756836, "identity": 0.5976120233535767, "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_Contentment/0145760282cfb9fef425be8c3f747b7909e908904b98efd058060931ec2604f7.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "5424cb506f0f4c11fe7148e311f97b01fe9d3af5969e3b5ffd7bbc930ecc8519", "generation_seconds_batch": 14.857523272978142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0861027240753174, "target_z": 3.4375002440102724, "ce": 6.157639026641846, "genuineness": 4.432034492492676, "identity": 0.6294101476669312, "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_Contentment/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.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": "035ec572c347ce66cda110d2de6d4d610704bf7f720d446ae654e9e66c301411", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5c75776aaa950687c995581b36ad9154e2fff769831f10e4455de0938e1df7bd", "generation_seconds_batch": 14.459264880977571, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6213996410369873, "target_z": 4.4999998816919895, "ce": 6.213237762451172, "genuineness": 4.093128204345703, "identity": 0.6661680340766907, "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_Contentment/035ec572c347ce66cda110d2de6d4d610704bf7f720d446ae654e9e66c301411.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": "036f9c16d2f9284109c5669d815166e4af739f6e1704f7db5a02235bda005c34", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "4d6590416c53d928651ed7fb34273e6f21460a4548572440f9a92a0adb97e4a6", "generation_seconds_batch": 15.139024809002876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0703585147857666, "target_z": 3.4062498927833653, "ce": 6.125868320465088, "genuineness": 4.2374773025512695, "identity": 0.6066837906837463, "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_Contentment/036f9c16d2f9284109c5669d815166e4af739f6e1704f7db5a02235bda005c34.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "038f806b57d74bde67dd06f0668a019408db02632a65b17b2ec93810ce6f6dbf", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1bddf8aab88feb9ada4fec1a8a3a2b097d7d0977a208084f61ec3dc54da1cba4", "generation_seconds_batch": 19.386066977051087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0464885234832764, "target_z": 5.343749900177616, "ce": 6.062326908111572, "genuineness": 3.8797430992126465, "identity": 0.5779323577880859, "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_Contentment/038f806b57d74bde67dd06f0668a019408db02632a65b17b2ec93810ce6f6dbf.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": "03b8661afdbdebb4a6bef27d86442ffeb48daeb0088850c62ba5bd15c14d5520", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1805de6c53a5763ad73b0c80286d76b94fbca6103d92a971affc8d54738cd402", "generation_seconds_batch": 14.467049314989708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3380072116851807, "target_z": 3.937500184856267, "ce": 6.332377910614014, "genuineness": 4.20609712600708, "identity": 0.4782625734806061, "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_Contentment/03b8661afdbdebb4a6bef27d86442ffeb48daeb0088850c62ba5bd15c14d5520.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": "03cf526ddcc105c1906ad9c83dfefa9cfa8e54f546f146d7e85a93923dac542c", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "af839513f9626bcaae0cdf5388433814e0966b3dabfb574f8c7d2c5401eb8170", "generation_seconds_batch": 14.475030604051426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.078230619430542, "target_z": 3.421875068396819, "ce": 6.141753673553467, "genuineness": 4.68307638168335, "identity": 0.5579750537872314, "hypothesis": "Je écrit le numéro sur l'enveloppe, lis le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/03cf526ddcc105c1906ad9c83dfefa9cfa8e54f546f146d7e85a93923dac542c.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": "04056ca0c560dbaa50dff127c55955cd7e33a120168ffeae7a0ebbd49e7f9333", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "779ca7a97d5a2f59dcb51558d32f38e3e03a0958a6505e6455191b735abaca9a", "generation_seconds_batch": 15.100125383003615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.747351884841919, "target_z": 4.749999852114986, "ce": 6.2767791748046875, "genuineness": 4.005263805389404, "identity": 0.5975956916809082, "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_Contentment/04056ca0c560dbaa50dff127c55955cd7e33a120168ffeae7a0ebbd49e7f9333.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "040deaefe7f3be79cbf9ac5f4f2d8e7e2ef8808aef85043371d2e752618512e6", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9b66bfb17d95aa0f09b0c51bb65151f8fee894b296202a1373446b9a8289fd84", "generation_seconds_batch": 19.262782260077074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3852391242980957, "target_z": 4.031249818840858, "ce": 6.0305562019348145, "genuineness": 4.432034492492676, "identity": 0.6824405789375305, "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_Contentment/040deaefe7f3be79cbf9ac5f4f2d8e7e2ef8808aef85043371d2e752618512e6.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "04c0588bd56fa71eece1af21adf23b98b0db3113953bacf29d2bbb1b571dd78a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e5624c951f4ed10b9d6544cca4b3928efbc70563682b11a94a7483a12ef84f37", "generation_seconds_batch": 19.537826783023775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3852391242980957, "target_z": 4.031249818840858, "ce": 6.022613525390625, "genuineness": 4.1998209953308105, "identity": 0.7192195653915405, "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_Contentment/04c0588bd56fa71eece1af21adf23b98b0db3113953bacf29d2bbb1b571dd78a.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "04e475b35c12cce52f587595d8a4898534086d9504c15001cdf500fdde560af8", "bucket": "emo_Contentment", "phase": "wording", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "13fddfb73602f9c04ee59796165932768064ff97121b8df21a992053299a96f4", "generation_seconds_batch": 15.72162374400068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.235671043395996, "target_z": 3.734375268041587, "ce": 6.125868320465088, "genuineness": 4.482243061065674, "identity": 0.7642277479171753, "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_Contentment/04e475b35c12cce52f587595d8a4898534086d9504c15001cdf500fdde560af8.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "04fa8118351b068c6713c691a896f829bcd10f4e6e707fae5e6a2f40ef089dff", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f10bd5773088597a47aa4fadaca2d7af8aebe595b6480b14ab01a49de1b0e77f", "generation_seconds_batch": 19.85247933201026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8103280067443848, "target_z": 4.874999837326485, "ce": 6.078212261199951, "genuineness": 4.1998209953308105, "identity": 0.6139311790466309, "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_Contentment/04fa8118351b068c6713c691a896f829bcd10f4e6e707fae5e6a2f40ef089dff.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "0506048910099d3713679e9b948ace5b11584ab263f75282d8de2c15e88d9bb2", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ec34f6fcda30299aaa4eb3e8c935355da802685340de20231beb0409705b5181", "generation_seconds_batch": 23.375857010949403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6213996410369873, "target_z": 4.4999998816919895, "ce": 6.1894097328186035, "genuineness": 4.369274139404297, "identity": 0.5755478143692017, "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_Contentment/0506048910099d3713679e9b948ace5b11584ab263f75282d8de2c15e88d9bb2.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "05854ce5464921607276f6914000c714bee02db1b1eac9ff4171bc8ca6385d41", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ed1e13da654388b54286b107fb49bd15b22174674f1f9a3c81760caf1d7cd068", "generation_seconds_batch": 14.18425628496334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.43247127532959, "target_z": 4.124999926057493, "ce": 6.24500846862793, "genuineness": 4.243753433227539, "identity": 0.7760078310966492, "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_Contentment/05854ce5464921607276f6914000c714bee02db1b1eac9ff4171bc8ca6385d41.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "05883762d7d2ada83ee07b30ce950e6f13b0db1734029bc6dfb6744eacb2020f", "bucket": "emo_Contentment", "phase": "wording", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e8de84f0ea2a21089774ded6529ce3ce15bc80a452600fab4bfd4c14c464ab1d", "generation_seconds_batch": 15.950176565907896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2514150142669678, "target_z": 3.765625146036451, "ce": 6.308549880981445, "genuineness": 3.9299514293670654, "identity": 0.11400222778320312, "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_Contentment/05883762d7d2ada83ee07b30ce950e6f13b0db1734029bc6dfb6744eacb2020f.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "108173db81796a3fe95b385e079ed9565d830c9fb8e8239cf4bd811f70ecbea7", "generation_seconds_batch": 16.532820568885654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9758943319320679, "target_z": 3.2187499149661174, "ce": 6.372091293334961, "genuineness": 4.65797233581543, "identity": 0.6251670718193054, "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_Contentment/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "05cec9b3d2d8e29b809581bafe4faedf043925c06f7ade310ce4fb10795b2553", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "54e25650f999c3f81e5eabd2753af92e7d6f7802cc27098e3acccc5b5dfc452b", "generation_seconds_batch": 22.027468731976114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3852391242980957, "target_z": 4.031249818840858, "ce": 6.197352409362793, "genuineness": 3.9550557136535645, "identity": 0.4393407702445984, "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_Contentment/05cec9b3d2d8e29b809581bafe4faedf043925c06f7ade310ce4fb10795b2553.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "05f04b0db0ddd1d25949bce14b99c4e197060005f02606b418f9c5f6af349cd6", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "176d5e1c9e94b38928a3c6477f99c16b6277e6c837735c587917f0c9162a0a6a", "generation_seconds_batch": 20.478954209946096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7788400650024414, "target_z": 4.812500081336758, "ce": 6.252951145172119, "genuineness": 4.406930446624756, "identity": 0.6671425104141235, "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_Contentment/05f04b0db0ddd1d25949bce14b99c4e197060005f02606b418f9c5f6af349cd6.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "06563c9055fa1a28d6890d34c1329b4f2509507095a32cdbf7482970b9c9d0ef", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "1ea8aaea6346ba6184600ca8112374923bfa8ba230190a5dbc7cfad9b97ed11b", "generation_seconds_batch": 19.514460743987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6056556701660156, "target_z": 4.468750003697125, "ce": 6.046441555023193, "genuineness": 4.469690799713135, "identity": 0.5955215096473694, "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_Contentment/06563c9055fa1a28d6890d34c1329b4f2509507095a32cdbf7482970b9c9d0ef.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "066aac7ccd30fbc5b2874488ac458e9d6939beb9fb6c87c071acf5d22001c331", "bucket": "emo_Contentment", "phase": "wording", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "3c0ed4c297352ac28ad3e067c03d89dc039cb670674dc58e98198a83d3621c8d", "generation_seconds_batch": 15.634526391979307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3537511825561523, "target_z": 3.968750062851131, "ce": 6.332377910614014, "genuineness": 4.482243061065674, "identity": 0.5718910694122314, "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_Contentment/066aac7ccd30fbc5b2874488ac458e9d6939beb9fb6c87c071acf5d22001c331.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "0670d3fb47700c7688dae0b5d37f6bba4abc12bbc4ffb8649d6cb0033f71f5d0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a4ee7df0a11f8c35366e56c758d7a2cf143176e9953c2c6497f77498b683d295", "generation_seconds_batch": 14.680334377917461, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2674129009246826, "target_z": 1.8124999630287466, "ce": 6.141753673553467, "genuineness": 4.093128204345703, "identity": 0.7587155103683472, "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_Contentment/0670d3fb47700c7688dae0b5d37f6bba4abc12bbc4ffb8649d6cb0033f71f5d0.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": "06d90be736fd68d12b2ef789c66426a4fc2d60dc91824bf4c59297d2496f3113", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f90458b4939ce6db2d9b33a00271ecad9efa4ec45ebe48a22bca13cd3d8ad6b8", "generation_seconds_batch": 14.398295005084947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.212054967880249, "target_z": 3.68750021443327, "ce": 6.252951145172119, "genuineness": 4.457139015197754, "identity": 0.7565397620201111, "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_Contentment/06d90be736fd68d12b2ef789c66426a4fc2d60dc91824bf4c59297d2496f3113.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": "071458c7b89a888696f7899bef8ebca69916ce187e682d740d7f86a4c431470f", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "aab44ecc879ad9fef206cd070ed818f011800996cdd8b1beb282d4c401a2c389", "generation_seconds_batch": 14.67772887693718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0467424392700195, "target_z": 3.3593748391750475, "ce": 6.197352409362793, "genuineness": 4.21237325668335, "identity": 0.6322354078292847, "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_Contentment/071458c7b89a888696f7899bef8ebca69916ce187e682d740d7f86a4c431470f.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "073b17efdfe71ba82558431ba8d2e0a049d810062777e8633b843bc12b12c6ea", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "607123f97ec7eec4c27717894c87389331b40ee36f4026468c0302f5f09618ab", "generation_seconds_batch": 19.55830460798461, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.574167490005493, "target_z": 4.406249774475354, "ce": 6.308549880981445, "genuineness": 4.005263805389404, "identity": 0.2167724072933197, "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_Contentment/073b17efdfe71ba82558431ba8d2e0a049d810062777e8633b843bc12b12c6ea.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": "0755e9ba43d911e034038e51ac9613524f8c641c97448bbe09d8bdc9f72672e5", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "977387dd63d56f7022a00daa2c428db057b73dd149c2a5196c945bdf73a2a1cc", "generation_seconds_batch": 14.535463180975057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.212054967880249, "target_z": 3.68750021443327, "ce": 6.24500846862793, "genuineness": 4.250029563903809, "identity": 0.6286015510559082, "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_Contentment/0755e9ba43d911e034038e51ac9613524f8c641c97448bbe09d8bdc9f72672e5.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "0803cd5ea164aadc96b540901d4fe82196d6e0ff3f5275aea54666dc70b8fbd5", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "6a64f95a1af340eb56a459fb99b75255af307c663432fdaa2237f86c6d3800c5", "generation_seconds_batch": 23.034723059972748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.369495153427124, "target_z": 3.9999999408459948, "ce": 6.165581703186035, "genuineness": 4.293961524963379, "identity": 0.5857585072517395, "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_Contentment/0803cd5ea164aadc96b540901d4fe82196d6e0ff3f5275aea54666dc70b8fbd5.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "0828b93cb07d86564ab84b55ac6f217ff5c3e41414a381b1caca3679074c914c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "668dfe6eb44a3da106875689a4844eb2c7c289508b4d3b992938139e813e56b9", "generation_seconds_batch": 14.611408349010162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.991638422012329, "target_z": 3.2500000295770026, "ce": 6.229123115539551, "genuineness": 4.15588903427124, "identity": 0.5254952311515808, "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_Contentment/0828b93cb07d86564ab84b55ac6f217ff5c3e41414a381b1caca3679074c914c.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "0860eb283fbf4dd029f94e1c544f6647942d854b03422be8ca11cea8b77be346", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "eef7a04ca7e478dedd1115518b503c7fbe62e2c295fcb68a3eea915ca2c3fb83", "generation_seconds_batch": 19.55234413407743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.479703426361084, "target_z": 4.218750033274128, "ce": 6.284721851348877, "genuineness": 3.9425034523010254, "identity": 0.24118471145629883, "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_Contentment/0860eb283fbf4dd029f94e1c544f6647942d854b03422be8ca11cea8b77be346.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "095e72e6c8b17de138eea8b0c715b5da25ffe397ec0fdc1e636caedac023b24f", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "5842ae6222e88ab716536bb01e57889ec7654092238492d01afde3bd5a262599", "generation_seconds_batch": 20.2394188469043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6213996410369873, "target_z": 4.4999998816919895, "ce": 6.133810997009277, "genuineness": 4.1998209953308105, "identity": 0.09947098791599274, "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_Contentment/095e72e6c8b17de138eea8b0c715b5da25ffe397ec0fdc1e636caedac023b24f.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": "097b061bcec3ccb1182bc005260df4ba6a816bf278a76088b7dffc74c20ee291", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "176972354fb24f15a77ecf295c251269642e2dfb23850621d26ad5fd91e79bb4", "generation_seconds_batch": 14.390597870922647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1805667877197266, "target_z": 3.6249999852114985, "ce": 6.173524379730225, "genuineness": 4.507347106933594, "identity": 0.8527002334594727, "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_Contentment/097b061bcec3ccb1182bc005260df4ba6a816bf278a76088b7dffc74c20ee291.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": "09d93da9c5fa5d02f7eeb9533de74437baf666f7234e7965b2d46aa68d1a75c4", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aca7d3f9fdbb75ba8cda2d72b00fddbc59b40f016ef649fd040ff7e9c320d103", "generation_seconds_batch": 14.475030604051426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.259286880493164, "target_z": 3.781249848417861, "ce": 5.982900142669678, "genuineness": 4.432034492492676, "identity": 0.786402702331543, "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_Contentment/09d93da9c5fa5d02f7eeb9533de74437baf666f7234e7965b2d46aa68d1a75c4.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "09fb6253c46f77553b62989e0ebe12d7bb70b5ae9eb11b936c1e72fd30aad880", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a7f9742eece80188bae7bee4194455efa9c2c0ef317269c5e7200596de4a37b6", "generation_seconds_batch": 21.34214420907665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.589911699295044, "target_z": 4.437500125702262, "ce": 6.324435234069824, "genuineness": 4.21237325668335, "identity": 0.3528393507003784, "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_Contentment/09fb6253c46f77553b62989e0ebe12d7bb70b5ae9eb11b936c1e72fd30aad880.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": "0a07d17b8d1e43299bde4242c65a657cba290f8995d43511235cf075ca68dd9f", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "58deb8d9162b99c9e17b2c42a3f60d4c4074aca5680567916dec06c5ea5f3ec1", "generation_seconds_batch": 19.222941415035166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.235671043395996, "target_z": 3.734375268041587, "ce": 6.23706579208374, "genuineness": 4.356721878051758, "identity": 0.5395342111587524, "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_Contentment/0a07d17b8d1e43299bde4242c65a657cba290f8995d43511235cf075ca68dd9f.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "0a616d6a4e6e8d8f769117c92240e1a04defd9ee8ee7a62a3816dcd3a5a7c546", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7bd31aec395bf06f5a2c03e3e51daa28a3f492397f1e080c6227432faeecc433", "generation_seconds_batch": 19.626081667025574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7158639430999756, "target_z": 4.687500096125259, "ce": 6.499174118041992, "genuineness": 4.319066047668457, "identity": 0.27872776985168457, "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_Contentment/0a616d6a4e6e8d8f769117c92240e1a04defd9ee8ee7a62a3816dcd3a5a7c546.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "0aaacfcc1ffc2985d689abff20321dd53163f1b242cf72dcd530740115b9ecd8", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1618f30a7c6819409690545f9a3b2f0e2e96f1519f2613115fa4619c9e606b09", "generation_seconds_batch": 21.692667067050934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5584235191345215, "target_z": 4.374999896480491, "ce": 6.038498878479004, "genuineness": 4.381826400756836, "identity": 0.6239992380142212, "hypothesis": "I've done the pet boy. It was pretty fenêtre. We've got what she contained.", "wer": 0.9473684210526315, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/0aaacfcc1ffc2985d689abff20321dd53163f1b242cf72dcd530740115b9ecd8.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "0ae2ec36e8323c8d1959f6bef41c57f974b4870097cbc2e8c09ff3a720d24b21", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "cced0b7fd5e18c5935347a3325351fd2c3995bef641f8b8184a91c55739be63c", "generation_seconds_batch": 20.540258308988996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9601503610610962, "target_z": 3.1875000369712536, "ce": 6.062326908111572, "genuineness": 4.18726921081543, "identity": 0.36383265256881714, "hypothesis": "De deur staat nog open. Ik heb je jou op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/0ae2ec36e8323c8d1959f6bef41c57f974b4870097cbc2e8c09ff3a720d24b21.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": "0b924bea89ab7adb5721937c9f2f10ef5bcafa6e87e35459f25819b9112d16a4", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Someone moved the little blue chair.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d302d5348be653962ef1108659d93c675ed1fa9d90ee2572bfc38339c0f67a8e", "generation_seconds_batch": 19.481856803991832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.526935577392578, "target_z": 4.312500140490763, "ce": 6.372091293334961, "genuineness": 4.2374773025512695, "identity": 0.17717988789081573, "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_Contentment/0b924bea89ab7adb5721937c9f2f10ef5bcafa6e87e35459f25819b9112d16a4.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": "0bcd629cea1fb97fce1ece0192a60152cad6954a26470342808a90bceb8ce350", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cd645ff730f18b8bde869d0038e46a479e5465efc6888b06a72b3828589fbb49", "generation_seconds_batch": 19.72013212798629, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3143911361694336, "target_z": 3.8906251312479494, "ce": 6.141753673553467, "genuineness": 4.325342178344727, "identity": 0.47237178683280945, "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_Contentment/0bcd629cea1fb97fce1ece0192a60152cad6954a26470342808a90bceb8ce350.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "0bfa21b230c97513a087164dec597685f8406e1f36b916b90aebfc1a46db290c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "7fe436c36f742dc65498f763591e997a3db3da0d2710bb537dc8dd6d8765b8c6", "generation_seconds_batch": 19.837481519090943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.684375762939453, "target_z": 4.6249998669034875, "ce": 6.24500846862793, "genuineness": 4.218649387359619, "identity": 0.38472825288772583, "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_Contentment/0bfa21b230c97513a087164dec597685f8406e1f36b916b90aebfc1a46db290c.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": "0c1fb1afc3c42f60cd9effe2daabf7f14a56a6766f2db2342c87e9674eadb96e", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Your message arrived after I had left.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "e26ec808e2767711f76c3c464f26618e7fa6880c44181902c3a3a1478a5f17b6", "generation_seconds_batch": 14.350991728017107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.282902956008911, "target_z": 3.8281249020261785, "ce": 6.499174118041992, "genuineness": 4.394378662109375, "identity": 0.3720664978027344, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/0c1fb1afc3c42f60cd9effe2daabf7f14a56a6766f2db2342c87e9674eadb96e.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "0c6115514c19b28661ffa26fe1cc4595615a68afbbde859f941b4b39dd46c74e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8a122f9d505d7061cfc17470c2d2439bfb92a8c3c5ff1e574a2f0ba7f4974465", "generation_seconds_batch": 20.908456837991253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.700119733810425, "target_z": 4.656249744898352, "ce": 6.252951145172119, "genuineness": 4.419482707977295, "identity": 0.5814936757087708, "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_Contentment/0c6115514c19b28661ffa26fe1cc4595615a68afbbde859f941b4b39dd46c74e.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "0c6a06319c3001331c78ee8d7d69ddc2f10ab23dda6e87deaebedec1903912e2", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "9b2deb71be640eaa0039d710fb36b083dbeb139d5f5c693d880554db3c40c528", "generation_seconds_batch": 19.514460743987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.637143611907959, "target_z": 4.531249759686853, "ce": 6.054384231567383, "genuineness": 4.570107460021973, "identity": 0.6560409665107727, "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_Contentment/0c6a06319c3001331c78ee8d7d69ddc2f10ab23dda6e87deaebedec1903912e2.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": "0c7bd6181019c0b3e06405cce10312577e6d4ed692a2c7ba6134aaa9add9077e", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "dc30f3b4070a3523a8fe5503c1bd69382b965c462d9fdab22fd104259aa2fbf3", "generation_seconds_batch": 15.18735123402439, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.479703426361084, "target_z": 4.218750033274128, "ce": 6.173524379730225, "genuineness": 4.18099308013916, "identity": 0.5723271369934082, "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_Contentment/0c7bd6181019c0b3e06405cce10312577e6d4ed692a2c7ba6134aaa9add9077e.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "390e807c21f269aaa76fe74fabae5ce22c78eab4e3b2e69e352f95cd43c675be", "generation_seconds_batch": 14.30846586509142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8420701026916504, "target_z": 2.953125005545688, "ce": 6.173524379730225, "genuineness": 4.419482707977295, "identity": 0.7277483344078064, "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_Contentment/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "0ce6c7c78bfeb0a1ebd97774f3bbe2a39188224b7f144c4b4afddf28f5d2c302", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "7d7686f5a6242a42fe42fcc9196178ae5894680afbceec4a48f82486136620d3", "generation_seconds_batch": 20.625577620929107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3852391242980957, "target_z": 4.031249818840858, "ce": 6.141753673553467, "genuineness": 4.545003414154053, "identity": 0.6420091390609741, "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_Contentment/0ce6c7c78bfeb0a1ebd97774f3bbe2a39188224b7f144c4b4afddf28f5d2c302.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "0dbc3651feb398cead9232ad49d80b80dc133e1ecc0f75d1cd4f80631ce8af2e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "7e8e389e1225d8df150a90f9db5e1efc01023253e66558f7e4b6144b182f83b4", "generation_seconds_batch": 19.69721358199604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.275031089782715, "target_z": 3.8125001996447683, "ce": 5.95112943649292, "genuineness": 3.8922953605651855, "identity": 0.527840793132782, "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_Contentment/0dbc3651feb398cead9232ad49d80b80dc133e1ecc0f75d1cd4f80631ce8af2e.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "0dc39ebcf6957f2a18636487a7e063c751649e155550e5157a04e4d84452dd71", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e818411ef51105b53edcab3426fae9fe7b94357350f41ab654e1d6b9e1f1839f", "generation_seconds_batch": 19.4048111140728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3537511825561523, "target_z": 3.968750062851131, "ce": 6.205295085906982, "genuineness": 4.111956596374512, "identity": 0.25670796632766724, "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_Contentment/0dc39ebcf6957f2a18636487a7e063c751649e155550e5157a04e4d84452dd71.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "0dda6bf24939120ef93feed46ff42afbf79f070511aebf313672be5546085069", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "40ebba198714f12a939249284c5a237ea3c82dc3ee6828968fb13f3d70176da0", "generation_seconds_batch": 14.8290553529514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4009833335876465, "target_z": 4.062500170067765, "ce": 6.0305562019348145, "genuineness": 4.356721878051758, "identity": 0.6634433269500732, "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_Contentment/0dda6bf24939120ef93feed46ff42afbf79f070511aebf313672be5546085069.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "0de6698191fc1c744015ce699787a8cccf920961f046886269636e775d83d6df", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "0cff4858257dbf93182348b6e762b24926b3b11540270bdb973cc79db5b442d0", "generation_seconds_batch": 14.990697697037831, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1963107585906982, "target_z": 3.6562498632063622, "ce": 6.2767791748046875, "genuineness": 3.8922953605651855, "identity": 0.2885306179523468, "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_Contentment/0de6698191fc1c744015ce699787a8cccf920961f046886269636e775d83d6df.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "0e68a05d6ea58b469bb03183faeb1ea2dcce586e75f1a0c6da35aebcfd839454", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "488643178fc1e22ac8290721c0c595cb047b47d25546aab93d926d38404c4b05", "generation_seconds_batch": 20.562167907948606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8105820417404175, "target_z": 2.890625012939939, "ce": 6.229123115539551, "genuineness": 4.362998008728027, "identity": 0.7016879916191101, "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_Contentment/0e68a05d6ea58b469bb03183faeb1ea2dcce586e75f1a0c6da35aebcfd839454.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "10a26f287107cb4f893450765c796995e524dd9bfe219bc6f56f13643ac4c8e9", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "1e237e0fac3db4782433df746da1590f818d03f519d6eb6f1a775dbb56f1cc5a", "generation_seconds_batch": 14.547752770013176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6846297979354858, "target_z": 2.6406250425169415, "ce": 6.109982967376709, "genuineness": 4.250029563903809, "identity": 0.7103502154350281, "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_Contentment/10a26f287107cb4f893450765c796995e524dd9bfe219bc6f56f13643ac4c8e9.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "10e85d4bd995db6137578c81d23e5e7923d4387c21f5345413ef2900e08f98a7", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "da5516ec3b129701814c188b49635ea9f5c58ddbc9276835a8fccfa4a19b41fe", "generation_seconds_batch": 19.77650257491041, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5111913681030273, "target_z": 4.281249789263856, "ce": 5.871703147888184, "genuineness": 4.074300289154053, "identity": 0.5842477083206177, "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_Contentment/10e85d4bd995db6137578c81d23e5e7923d4387c21f5345413ef2900e08f98a7.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "12474dbed938262fe7ad9869b0ef5e47922591fdce420e4d55a0f5c71180f31f", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "afccce4b985180450feb962d21286f961b915f32a7ab9a872dbc58201d65bf8f", "generation_seconds_batch": 23.375857010949403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.43247127532959, "target_z": 4.124999926057493, "ce": 6.1894097328186035, "genuineness": 4.532451152801514, "identity": 0.4689621031284332, "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_Contentment/12474dbed938262fe7ad9869b0ef5e47922591fdce420e4d55a0f5c71180f31f.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "5fd45887fdcf63503c8f12a03c62aacaa36925606b8057a99cf734669bf5389a", "generation_seconds_batch": 14.445116898976266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2277989387512207, "target_z": 3.7187500924281336, "ce": 6.133810997009277, "genuineness": 4.287685871124268, "identity": 0.6387292742729187, "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_Contentment/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "130da0b180e9a900bd83f2316da8c6c5006fb9c08c2b939a5ac6f09b6ef8bc65", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c6d104deecbb07d28bd50c16cec04049eefe299c3aedcedf0290f3682c4d8abd", "generation_seconds_batch": 19.476461504003964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1963107585906982, "target_z": 3.6562498632063622, "ce": 6.260893821716309, "genuineness": 4.256305694580078, "identity": 0.5532652139663696, "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_Contentment/130da0b180e9a900bd83f2316da8c6c5006fb9c08c2b939a5ac6f09b6ef8bc65.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "133a63807eef96c18805a279da66e393a0093260a933dd42dd9672cd8f8ff1b2", "bucket": "emo_Contentment", "phase": "wording", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f04b1b9346d009071c0e33342a474e2489d1bfb9693c7e0530c03419a77c3cd5", "generation_seconds_batch": 19.71246002695989, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0624866485595703, "target_z": 3.390625190401955, "ce": 6.181467056274414, "genuineness": 4.356721878051758, "identity": 0.5270370244979858, "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_Contentment/133a63807eef96c18805a279da66e393a0093260a933dd42dd9672cd8f8ff1b2.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "138a4bd46e0df0ed89bc614a5cf02e28742643224fa9055eb920a0fdd838271b", "bucket": "emo_Contentment", "phase": "wording", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e9f17f11034708950abe59a34d6726adabe3bad5a9263d2acd61ae543f2782fc", "generation_seconds_batch": 15.72162374400068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6056556701660156, "target_z": 4.468750003697125, "ce": 6.086154937744141, "genuineness": 4.2249250411987305, "identity": 0.6655253767967224, "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_Contentment/138a4bd46e0df0ed89bc614a5cf02e28742643224fa9055eb920a0fdd838271b.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "139587d49e0a10e957c022426ad65872651fc25cd0d3139e6767befd939159c0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "eaf3fba3a323644f0b43c494bbc8b1e9bd768bb9ae6f3d9f90b414cde751b200", "generation_seconds_batch": 22.549040294950828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8777481317520142, "target_z": 1.039062524955596, "ce": 6.141753673553467, "genuineness": 4.256305694580078, "identity": 0.5622789859771729, "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_Contentment/139587d49e0a10e957c022426ad65872651fc25cd0d3139e6767befd939159c0.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "1413de8454669ec032f7e601dbbb2d7942c58f9be2f551e8a0d9afc8ef7b6df2", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ac29c9cab4af8148c14af309c5dbf8bcce8226f2c52670ec6e66b1d9ce6930a1", "generation_seconds_batch": 22.00115426001139, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.345879077911377, "target_z": 3.953124887237677, "ce": 6.157639026641846, "genuineness": 4.381826400756836, "identity": 0.6150688529014587, "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_Contentment/1413de8454669ec032f7e601dbbb2d7942c58f9be2f551e8a0d9afc8ef7b6df2.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "14894ed608b0c9fb95216b67c7c72fb7d7bd5fe3a22b0699d2558f045f7a1f4a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "96331f6dcef725995d4b16c498cd0c2e9e9cf945eac0165df3863604221fb011", "generation_seconds_batch": 14.35594613198191, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4482152462005615, "target_z": 4.156249804052357, "ce": 6.117925643920898, "genuineness": 4.545003414154053, "identity": 0.7082717418670654, "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_Contentment/14894ed608b0c9fb95216b67c7c72fb7d7bd5fe3a22b0699d2558f045f7a1f4a.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "14b9d0fa2fd92883411865f49a0986c1345b5343c195237b024b2af98744fe9a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "423ce372f5010abe3914b089fb73085829c6fe86ca8c97354f0ff37432f17b04", "generation_seconds_batch": 19.63312729401514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.369495153427124, "target_z": 3.9999999408459948, "ce": 6.062326908111572, "genuineness": 4.65797233581543, "identity": 0.5800827741622925, "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_Contentment/14b9d0fa2fd92883411865f49a0986c1345b5343c195237b024b2af98744fe9a.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "b7c8c57b18bbacc3761fd95a46f79afc21c5458769411ba631cb3e7be444aeab", "generation_seconds_batch": 16.40034889895469, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9837663173675537, "target_z": 3.234374853963549, "ce": 6.348263263702393, "genuineness": 4.268857479095459, "identity": 0.6553011536598206, "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_Contentment/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "15a6d6b8eb2c53f613a1766b9fcb684befbf24bd99039b1a5d81b08bd13f0feb", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "c6227ec385200628285bc7120dfddc621adfb9b1074d73916212319a918c40b0", "generation_seconds_batch": 16.403993866057135, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4639594554901123, "target_z": 4.187500155279264, "ce": 6.324435234069824, "genuineness": 4.325342178344727, "identity": 0.45014408230781555, "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_Contentment/15a6d6b8eb2c53f613a1766b9fcb684befbf24bd99039b1a5d81b08bd13f0feb.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "15aa46477005cb5b09195f74f070433aad1da979b969dc9ebb972f604502abfa", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "56d8069e07bad25f50d32075c9670e979438c8874019f77cf89f4ec27f219a3f", "generation_seconds_batch": 23.161672211950645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.306519031524658, "target_z": 3.874999955634496, "ce": 6.125868320465088, "genuineness": 4.293961524963379, "identity": 0.6752263903617859, "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_Contentment/15aa46477005cb5b09195f74f070433aad1da979b969dc9ebb972f604502abfa.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "15e1e25ad501f2fdddf0029d4b29bddeea2cf939999963454017e9606602650d", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "054a07e1fae94c5a20b23a1bba8111dd7e540fa99d28c300ba0a1c3afd2fc6b1", "generation_seconds_batch": 20.046449268003926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7158639430999756, "target_z": 4.687500096125259, "ce": 6.284721851348877, "genuineness": 4.262581825256348, "identity": 0.3638964891433716, "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_Contentment/15e1e25ad501f2fdddf0029d4b29bddeea2cf939999963454017e9606602650d.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "16753ba612cac56955ec09c433712714dc78a46feb692a89723f4fad4c2da513", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a4798dffa3817a51640b6cfcf687ffa3b8bdb85a5243d4d159ee700851ec6356", "generation_seconds_batch": 19.060159850982018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.235671043395996, "target_z": 3.734375268041587, "ce": 6.229123115539551, "genuineness": 4.325342178344727, "identity": 0.5443702340126038, "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_Contentment/16753ba612cac56955ec09c433712714dc78a46feb692a89723f4fad4c2da513.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "1722bc8f8cdecf3d032f758bd2463bfb66be2758571f5a8829f274ef284e4ee0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "617df706f69a6ad1a1888ddc3e632b7aa351440aabe9e3b055515f85475b9310", "generation_seconds_batch": 19.837481519090943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6528878211975098, "target_z": 4.56250011091376, "ce": 6.229123115539551, "genuineness": 4.250029563903809, "identity": 0.31202268600463867, "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_Contentment/1722bc8f8cdecf3d032f758bd2463bfb66be2758571f5a8829f274ef284e4ee0.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "179c0cd6d45b65858dd398dbaa02d4140339833d9beab45dddb56cc126205944", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ea21bb3e64f4e98099d2f3a4d1f7552506e76a4a31e598fb4e9b7ef6e9219c64", "generation_seconds_batch": 19.942965987953357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.054614543914795, "target_z": 3.3750000147885015, "ce": 6.197352409362793, "genuineness": 4.469690799713135, "identity": 0.8357892036437988, "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_Contentment/179c0cd6d45b65858dd398dbaa02d4140339833d9beab45dddb56cc126205944.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "17e0dfeb287fa63778714695a9c3355580cfdc9d011fb3c0ef372adf3bdc8e70", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "3903d13a97caf8175fb467905f4cdd02e6b74a4ef992bb2806327b4c95e094ae", "generation_seconds_batch": 22.172423996031284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6528878211975098, "target_z": 4.56250011091376, "ce": 5.974957466125488, "genuineness": 4.162164688110352, "identity": 0.5952566862106323, "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_Contentment/17e0dfeb287fa63778714695a9c3355580cfdc9d011fb3c0ef372adf3bdc8e70.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "1830a1a70a393d9f4b5d2a48a53844fc8f1a94af4f58277c852deae3fc9e0498", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a902aeda47ce155ea89b9d0d412cecc735a4c56d2209e080fa6d254328bc1c7e", "generation_seconds_batch": 19.05873520905152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9522782564163208, "target_z": 3.1718748613577996, "ce": 6.213237762451172, "genuineness": 4.093128204345703, "identity": 0.6127097606658936, "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_Contentment/1830a1a70a393d9f4b5d2a48a53844fc8f1a94af4f58277c852deae3fc9e0498.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "18b8574a5e42e2f913b5e847ec43fd306c8798fddc33e0da86da848fc31a4b97", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "348a7de14c8b53b40cb33da17c28538d8b3a002a497f0c9a482299eecc12221b", "generation_seconds_batch": 14.680334377917461, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3303890228271484, "target_z": 1.9374999482402453, "ce": 6.1020402908325195, "genuineness": 4.413206577301025, "identity": 0.5415005683898926, "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_Contentment/18b8574a5e42e2f913b5e847ec43fd306c8798fddc33e0da86da848fc31a4b97.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "19aec36990860902634ffbd3db802b715a8ee75057c32e127c2d45ff81eb6093", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "3a64553903bbe73e02f5bb7c18c6ff710c82cb024fb76413cde8c3cefe3c1697", "generation_seconds_batch": 21.90929864696227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7712218761444092, "target_z": 2.812499844720736, "ce": 6.23706579208374, "genuineness": 4.344170093536377, "identity": 0.6056225299835205, "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_Contentment/19aec36990860902634ffbd3db802b715a8ee75057c32e127c2d45ff81eb6093.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "19bc6a5bb46b68afd7f25756cb99234bcc59a1578c2e575d3dedd5da05a1d0d7", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "46b6364d7b21be28bb1e8e253a980e8cbabc413a13acb0669e75f38d58d799b9", "generation_seconds_batch": 14.30923743499443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.007382392883301, "target_z": 3.2812499075718664, "ce": 6.165581703186035, "genuineness": 4.457139015197754, "identity": 0.7491785287857056, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/19bc6a5bb46b68afd7f25756cb99234bcc59a1578c2e575d3dedd5da05a1d0d7.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "1aed2f7d3e18d28c5899a07562f0ff1f44c29b09d5f6547c194caa51ae9194b0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "080140d18b8044356c4fad48af02733508194f8a866993c24c86fad7a566eba1", "generation_seconds_batch": 23.683720311964862, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0703585147857666, "target_z": 3.4062498927833653, "ce": 6.356205940246582, "genuineness": 3.9801597595214844, "identity": 0.5872807502746582, "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_Contentment/1aed2f7d3e18d28c5899a07562f0ff1f44c29b09d5f6547c194caa51ae9194b0.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "1b433eda9a8c51fb0b45493b44e5b444134ef5f447d33867a282c20b208c60bb", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "717ac614c6da5e07ae69a2a861bcc5cbaddda7fecfdcaddba8301e99e16c1c26", "generation_seconds_batch": 20.42362422903534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4009833335876465, "target_z": 4.062500170067765, "ce": 6.221180438995361, "genuineness": 4.174716949462891, "identity": 0.5946938395500183, "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_Contentment/1b433eda9a8c51fb0b45493b44e5b444134ef5f447d33867a282c20b208c60bb.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "1b8aa2ee3cf4f4dfd969566b4480e2dc9bad7d186f413c93e2d708bb92b31731", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "8fd5487039476f1aae540add9c059ea9c89d89dcf5dd605d29c2f4f37df2690c", "generation_seconds_batch": 19.6763041629456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9050462245941162, "target_z": 3.078124990757187, "ce": 6.213237762451172, "genuineness": 4.469690799713135, "identity": 0.5060682892799377, "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_Contentment/1b8aa2ee3cf4f4dfd969566b4480e2dc9bad7d186f413c93e2d708bb92b31731.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "1c68a3126f7e8d8387c71eb68d1ecf7109c518408a548d039152fed357b0a358", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "642cd7a86520d0ff2c25bff0aa247fd0e599d78403e5a76ed93b5e6bdee41d2f", "generation_seconds_batch": 23.744477748987265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1805667877197266, "target_z": 3.6249999852114985, "ce": 6.1020402908325195, "genuineness": 4.055472373962402, "identity": 0.6233426928520203, "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_Contentment/1c68a3126f7e8d8387c71eb68d1ecf7109c518408a548d039152fed357b0a358.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "1d00c8b8cd984b8115a425a7347449dafe4775ea9d11c9c11eb981b05712c28a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2d215efee4208b045265e6c93c42d205bc43e3104f95244241d4497589c97098", "generation_seconds_batch": 20.20043969503604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.235671043395996, "target_z": 3.734375268041587, "ce": 6.395919322967529, "genuineness": 4.532451152801514, "identity": 0.5529034733772278, "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_Contentment/1d00c8b8cd984b8115a425a7347449dafe4775ea9d11c9c11eb981b05712c28a.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "6dcdc424c1b1d80eba40b87aec9d14c2829cae3273adade325ea397ad37e6efe", "generation_seconds_batch": 14.43822749692481, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.007382392883301, "target_z": 3.2812499075718664, "ce": 6.316492557525635, "genuineness": 4.18099308013916, "identity": 0.6534286737442017, "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_Contentment/1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "1d8289b417e86156d77d1f3c875f59526c496c08546b2e75b7ee2585068795a1", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9807842c14613a111bd9ebd041bf08a866c2eb7849e238770c774d01034014eb", "generation_seconds_batch": 19.968201812007464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7911559343338013, "target_z": 0.86718748613578, "ce": 6.054384231567383, "genuineness": 4.061748504638672, "identity": 0.5375956296920776, "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_Contentment/1d8289b417e86156d77d1f3c875f59526c496c08546b2e75b7ee2585068795a1.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "d07574afaca4beff485e78e8a10805d88120a2cdc7426ea7c434f917702ea4bc", "generation_seconds_batch": 16.557714855996892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.944406270980835, "target_z": 3.156249922360368, "ce": 6.332377910614014, "genuineness": 4.632867813110352, "identity": 0.6085615158081055, "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_Contentment/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "1dccf500061f91161473ce8a5391092954c4b9524bdc5cf535e162749a276c12", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "6057eee317934e2c2fc48d3487935397bbd00af713ddf95e5b7bdafee5e4c097", "generation_seconds_batch": 19.183279406046495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4009833335876465, "target_z": 4.062500170067765, "ce": 5.895530700683594, "genuineness": 3.8044304847717285, "identity": 0.552812397480011, "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_Contentment/1dccf500061f91161473ce8a5391092954c4b9524bdc5cf535e162749a276c12.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "1dd8536f04ef4f10f9f91eb4cdf9c48cb83f4250da6d4f98710f160fb79dc0ae", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b3cfad0a80c66b80e76a6af3184baaf5dee4879e0a1bd18d05d216c8592e84f8", "generation_seconds_batch": 14.520092447986826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.306519031524658, "target_z": 3.874999955634496, "ce": 6.538887023925781, "genuineness": 4.293961524963379, "identity": 0.4911381006240845, "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_Contentment/1dd8536f04ef4f10f9f91eb4cdf9c48cb83f4250da6d4f98710f160fb79dc0ae.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "1de37b52d46a5be83e495987762d3b9d06c7e761903977efe43211f52652d9c7", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "5f4e867abf7b1576ece2e4fbef12f187bdfb9f9a16cbb0f4efd0fd1fb7f1cd7b", "generation_seconds_batch": 19.6763041629456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0624866485595703, "target_z": 3.390625190401955, "ce": 6.356205940246582, "genuineness": 4.7081804275512695, "identity": 0.44650864601135254, "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_Contentment/1de37b52d46a5be83e495987762d3b9d06c7e761903977efe43211f52652d9c7.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "1e3434ed280fc4e295661b02e2e9ad63910bdca11d3b80ae56576f1c7127dff0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "495f3c414599621999783699e8604307bdea948d87cc4d243d357e6bffb914c1", "generation_seconds_batch": 22.875912555959076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.275031089782715, "target_z": 3.8125001996447683, "ce": 5.967014789581299, "genuineness": 4.005263805389404, "identity": 0.44981423020362854, "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_Contentment/1e3434ed280fc4e295661b02e2e9ad63910bdca11d3b80ae56576f1c7127dff0.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "a630195e80fcb42f8b504fcc7154b347795d731e5aced1180abd7df4221f71c4", "generation_seconds_batch": 14.43822749692481, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9601503610610962, "target_z": 3.1875000369712536, "ce": 6.221180438995361, "genuineness": 4.457139015197754, "identity": 0.607177734375, "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_Contentment/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "1ec6628cc987c29e985253cf16e73bacb6a4f6d7b36368acec562aca0a1af11e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ec487ae58369263485b3c318759698e77b32860873dd513bfc4dce0da81a6b6d", "generation_seconds_batch": 19.211536013055593, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3852391242980957, "target_z": 4.031249818840858, "ce": 6.268836498260498, "genuineness": 4.545003414154053, "identity": 0.6935807466506958, "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_Contentment/1ec6628cc987c29e985253cf16e73bacb6a4f6d7b36368acec562aca0a1af11e.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "1f2cda2cfe29a9591770e7e63817750e2ab05861bb25efee79b972bcf8e48981", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "db376c2163b7e3522f47e3e85e6e19f93fb92d7c972ea9226654c5bbe0cfd25b", "generation_seconds_batch": 19.808388652978465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.054614543914795, "target_z": 3.3750000147885015, "ce": 6.4515180587768555, "genuineness": 4.093128204345703, "identity": 0.5968053936958313, "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_Contentment/1f2cda2cfe29a9591770e7e63817750e2ab05861bb25efee79b972bcf8e48981.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "1f975e244f1d142d99a4372604c8cd31e1bd40851969de25b75b7b0ff9f1b999", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "ec9f46c2859efa546282f9f645cf66acfa1fcffa518308b6db371042dff3e32b", "generation_seconds_batch": 21.284363360027783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6213996410369873, "target_z": 4.4999998816919895, "ce": 6.252951145172119, "genuineness": 4.595211505889893, "identity": 0.5351362824440002, "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_Contentment/1f975e244f1d142d99a4372604c8cd31e1bd40851969de25b75b7b0ff9f1b999.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "2063693d98c60fc48c2f3a770c7142d28ed4aa1c0fbde6b03af8495dfd8987b4", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "3c3d115fc5510e3128c71dc7bc248ec6455784e2088c8086d55a26341cec2ab5", "generation_seconds_batch": 19.7755003280472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4639594554901123, "target_z": 4.187500155279264, "ce": 6.41180419921875, "genuineness": 4.281409740447998, "identity": 0.4557262659072876, "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_Contentment/2063693d98c60fc48c2f3a770c7142d28ed4aa1c0fbde6b03af8495dfd8987b4.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "218a9e296028c0493df756a685834e5a2db6b56dc5f92a89ea9d0a905b0a9b53", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1348c4a2536e0d173d11daa312770fa753a5ab806cfbbe8d037c937acf3ff0dc", "generation_seconds_batch": 19.968201812007464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.542933464050293, "target_z": 2.3593749574830585, "ce": 6.109982967376709, "genuineness": 4.444586753845215, "identity": 0.784821093082428, "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_Contentment/218a9e296028c0493df756a685834e5a2db6b56dc5f92a89ea9d0a905b0a9b53.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": "21ea3028265f27dfc50eeca4201e073b22d90216f0ab8b820228c304b0e562a9", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I wrote the number on the envelope.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1aa6b7533ece0cc3b5d2dde57fea49ac6258f7503e24e826d68eebaa9ecb8cc9", "generation_seconds_batch": 19.44601815205533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3301351070404053, "target_z": 3.921875009242813, "ce": 6.356205940246582, "genuineness": 4.218649387359619, "identity": 0.28984472155570984, "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_Contentment/21ea3028265f27dfc50eeca4201e073b22d90216f0ab8b820228c304b0e562a9.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "21f3fb5bdef4c528ae2de58c247f6a855832be7c72e2c86a12052230a1a1e89b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "530edc05181e47900836a49fcc5a0578e4c421525599cf83257f00cfa927f376", "generation_seconds_batch": 22.148466433980502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3537511825561523, "target_z": 3.968750062851131, "ce": 5.935244083404541, "genuineness": 3.823258876800537, "identity": 0.533379077911377, "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_Contentment/21f3fb5bdef4c528ae2de58c247f6a855832be7c72e2c86a12052230a1a1e89b.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "22389d011593a24818a6b4cd1296d9060d5fbbbd2995bce85ade6db4f206f791", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "cc0c029f55189da4c01ff076ffe6a956033c59d0372859389037fb2ea43ad1f6", "generation_seconds_batch": 24.36600613698829, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2041828632354736, "target_z": 3.6718750388198163, "ce": 6.054384231567383, "genuineness": 4.457139015197754, "identity": 0.7313492894172668, "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_Contentment/22389d011593a24818a6b4cd1296d9060d5fbbbd2995bce85ade6db4f206f791.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": "22ad678081e195a90edb3ffa2570e6673d6c791c8b440ee22565394dc0d038b5", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "40ba153a85789a600dc7d59eab96b7140a8bd64bcab56f5fa52562fc3f0621d5", "generation_seconds_batch": 19.417256820946932, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6528878211975098, "target_z": 4.56250011091376, "ce": 6.117925643920898, "genuineness": 4.432034492492676, "identity": 0.6061725616455078, "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_Contentment/22ad678081e195a90edb3ffa2570e6673d6c791c8b440ee22565394dc0d038b5.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "233ff3738a072079984f636af6080499b876d95a8b685d951f1192a9fd8d535c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1b4cf4aec0467e8bf9ff68950612bf9e723603fd01b9433199edf742be8c111b", "generation_seconds_batch": 21.889463757979684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6056556701660156, "target_z": 4.468750003697125, "ce": 6.443574905395508, "genuineness": 4.306513786315918, "identity": 0.4577643871307373, "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_Contentment/233ff3738a072079984f636af6080499b876d95a8b685d951f1192a9fd8d535c.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "2357c3a18869807128ac10b9adc25d8899eeb35f334d46c1588883d4143f2c2e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "0a2e491aad94f741c7ebf69e0213c2c3d2d5ee0b5814e325272fb7a1f31a2b20", "generation_seconds_batch": 19.55830460798461, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.637143611907959, "target_z": 4.531249759686853, "ce": 6.205295085906982, "genuineness": 3.6475296020507812, "identity": 0.19389286637306213, "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_Contentment/2357c3a18869807128ac10b9adc25d8899eeb35f334d46c1588883d4143f2c2e.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "23afa66c3119a87114c0d35d76b923c3c73bebdd9a037a422a3e9217f378f063", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "bf1c225f23a814fddf9d31913b526d5844ad461cc5460562e466e081967a1846", "generation_seconds_batch": 20.148076451965608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7788400650024414, "target_z": 4.812500081336758, "ce": 6.157639026641846, "genuineness": 4.532451152801514, "identity": 0.7177878618240356, "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_Contentment/23afa66c3119a87114c0d35d76b923c3c73bebdd9a037a422a3e9217f378f063.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": "23beb7229aa80c2420dfced56d241cbe7e2595dc44e0342e9d226fbf0b9aa25e", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2fca128f48ab4c989e8d7afe17578c932a4b7b42f558dc551b19eb7d106d5bf6", "generation_seconds_batch": 14.640034439973533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.125462770462036, "target_z": 3.5156251756134536, "ce": 6.316492557525635, "genuineness": 4.375550270080566, "identity": 0.5921787619590759, "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_Contentment/23beb7229aa80c2420dfced56d241cbe7e2595dc44e0342e9d226fbf0b9aa25e.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "23e447e0b19e38b275e309ab1203914d84245392c90a0c9c7e44c7449e0ab16c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e7b3bc85be9739d66d9ddb54eb328e84bea198249f53b006f9dcf863e2b310b0", "generation_seconds_batch": 19.93379837903194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7948379516601562, "target_z": 2.8593748983290532, "ce": 6.23706579208374, "genuineness": 4.331617832183838, "identity": 0.49597570300102234, "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_Contentment/23e447e0b19e38b275e309ab1203914d84245392c90a0c9c7e44c7449e0ab16c.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": "2453cc538073e04f4e8a133f6cc2ace37fd5b160f9fd85afec9a8605460ef61f", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d07ece75f775a9ddc9ccee0e17039d6645704da832d5d0bbcdf6004745f564a7", "generation_seconds_batch": 19.34451213805005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.574167490005493, "target_z": 4.406249774475354, "ce": 6.1894097328186035, "genuineness": 4.231201171875, "identity": 0.5662864446640015, "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_Contentment/2453cc538073e04f4e8a133f6cc2ace37fd5b160f9fd85afec9a8605460ef61f.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": "24c50bf61e7046a4c6f0366b4c45770b9ddf65e0f3ce3a671670920241adbab3", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "eb094f19b3147d09c83fa9205d1d8d9d23c21b4a7461d320ac6103fa0fdd4bdd", "generation_seconds_batch": 14.67772887693718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.149078845977783, "target_z": 3.562500229221771, "ce": 6.221180438995361, "genuineness": 4.300237655639648, "identity": 0.5496082901954651, "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_Contentment/24c50bf61e7046a4c6f0366b4c45770b9ddf65e0f3ce3a671670920241adbab3.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "254e4c4516a02c69d25a15b735978fb3163bb5102700e90b3342a561ae2c2fce", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "16d98f9e8333082365026c54fc816ba26a443ea0699abf6e9f8a9f53f9953e64", "generation_seconds_batch": 19.18508251500316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9837663173675537, "target_z": 3.234374853963549, "ce": 6.340320587158203, "genuineness": 4.419482707977295, "identity": 0.761644721031189, "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_Contentment/254e4c4516a02c69d25a15b735978fb3163bb5102700e90b3342a561ae2c2fce.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "256e34f3b0a7a4eaf2799250c126e239762b8aeb6ebda40c605f4a01d515c51d", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "212e11258a11c40a9e65dc70a459dd5a092f208460e87bd344254c8737f49450", "generation_seconds_batch": 20.284125469974242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6295256614685059, "target_z": 2.5312499963028747, "ce": 6.268836498260498, "genuineness": 4.457139015197754, "identity": 0.6530808210372925, "hypothesis": "Die Tür ist noch offen. Ich habe dein Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/256e34f3b0a7a4eaf2799250c126e239762b8aeb6ebda40c605f4a01d515c51d.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": "25719ec0c94f93f1e6312b2c60718fec5b18ca88ad60a9d874900c86716752ae", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f24ee05712f527d036a2bfa4e27daaabb53d641aeebda6cad0c7e4d400472088", "generation_seconds_batch": 14.429126259987243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3143911361694336, "target_z": 3.8906251312479494, "ce": 6.046441555023193, "genuineness": 4.18726921081543, "identity": 0.703268826007843, "hypothesis": "The route tourne à gauche après le pont, continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.05, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/25719ec0c94f93f1e6312b2c60718fec5b18ca88ad60a9d874900c86716752ae.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "25927c51aef329288f8826fd330f1e357bde3b5c733620ae20c674faf951dc37", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "896e1c97e5e5b5e42a9aba2b903d2ef3e7136562ffb18b187a7119235a90d43b", "generation_seconds_batch": 21.892920819926076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0861027240753174, "target_z": 3.4375002440102724, "ce": 6.419747352600098, "genuineness": 4.7458367347717285, "identity": 0.6248527765274048, "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_Contentment/25927c51aef329288f8826fd330f1e357bde3b5c733620ae20c674faf951dc37.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "25ceed0b39cdb1ea4f0385a21754f60e7d31725828055950ada3d09c5547ab4b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "acdc9cd8171797ce01c6136b64d8635b10570ed50885e82df9ba6fe69cba135a", "generation_seconds_batch": 19.93379837903194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0939745903015137, "target_z": 3.4531249463916827, "ce": 6.348263263702393, "genuineness": 4.494794845581055, "identity": 0.5434974431991577, "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_Contentment/25ceed0b39cdb1ea4f0385a21754f60e7d31725828055950ada3d09c5547ab4b.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "25e105f832ed758221cd10e52637f1fabd5d684e16d660a3ca6eae130ea1a91f", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "58f5c983af5825b6af038eaac2b72305a36037b399251a153c216eddf8410445", "generation_seconds_batch": 19.98108323093038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3537511825561523, "target_z": 3.968750062851131, "ce": 6.268836498260498, "genuineness": 3.936227321624756, "identity": 0.2815263867378235, "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_Contentment/25e105f832ed758221cd10e52637f1fabd5d684e16d660a3ca6eae130ea1a91f.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "26a5d9840505fa8f75c38ec428eaba967a9e41ad94eb3cfd46b16a0e51db83e2", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "3d288f573f546ba6ab45170141b476a5f8463c45f0488a204f2013a98c932124", "generation_seconds_batch": 21.82350979500916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.54267954826355, "target_z": 4.343750018485626, "ce": 6.09409761428833, "genuineness": 4.250029563903809, "identity": 0.6624457836151123, "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_Contentment/26a5d9840505fa8f75c38ec428eaba967a9e41ad94eb3cfd46b16a0e51db83e2.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "26ce23a9df2102f43e6289462fa8c299c9c0a48d3645603b018f990b9c4ff57a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f14dd4cc98ecc87db45da060bd9cba246ba1d4aecc2ec157538c7ee5055325dd", "generation_seconds_batch": 14.871062690974213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6295256614685059, "target_z": 2.5312499963028747, "ce": 6.2767791748046875, "genuineness": 4.331617832183838, "identity": 0.31892329454421997, "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_Contentment/26ce23a9df2102f43e6289462fa8c299c9c0a48d3645603b018f990b9c4ff57a.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "c6c08bf521b758fbf5ed7d98b1fc74fea9572c7f1f8beb903ad9a8f35906dd7f", "generation_seconds_batch": 14.43830605095718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3616230487823486, "target_z": 3.9843747652325407, "ce": 6.348263263702393, "genuineness": 4.457139015197754, "identity": 0.12525485455989838, "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_Contentment/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.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": "26d85a5a51a5e970171d804f4eafdf3efd5167a9983427caab119294cf5012aa", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b3382da1a1aaefc631851974d0fa07978957f263918ae4ef5d63756c61e0fa7d", "generation_seconds_batch": 19.24625567905605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.920790195465088, "target_z": 3.1093748687520506, "ce": 6.23706579208374, "genuineness": 3.9425034523010254, "identity": 0.7113483548164368, "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_Contentment/26d85a5a51a5e970171d804f4eafdf3efd5167a9983427caab119294cf5012aa.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "26e4b339b77b90811313c68744666f688598dc4336ef21485efa18e4d4193c3b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "4776ff28c0429327e701b7c46fe2250ae6e19664df4af976f58a76f3ed7f9af6", "generation_seconds_batch": 19.691007470013574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1097185611724854, "target_z": 3.4843748243865464, "ce": 5.959072113037109, "genuineness": 3.823258876800537, "identity": 0.5183755159378052, "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_Contentment/26e4b339b77b90811313c68744666f688598dc4336ef21485efa18e4d4193c3b.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "27a5b2ef1ff7e2d3542d62d874b2b878346b8a8eb7d3cf4f428914a2ce2b2ab9", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a4eb839b49d9cd3670dc1db7e5ebe008fc023714c78d3ea4452c57748d1a9f1c", "generation_seconds_batch": 16.83763305505272, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.306519031524658, "target_z": 3.874999955634496, "ce": 5.879645347595215, "genuineness": 3.8420867919921875, "identity": 0.3275432884693146, "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_Contentment/27a5b2ef1ff7e2d3542d62d874b2b878346b8a8eb7d3cf4f428914a2ce2b2ab9.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": "28473633763f00566c15ed041814d1bc292b53df31929b40c5a856d699e1aca0", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "99f7f680f8d9093d13879528585ec038c02ed68064ac4455110ae49ab3d51c87", "generation_seconds_batch": 15.052727816044353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.235671043395996, "target_z": 3.734375268041587, "ce": 5.982900142669678, "genuineness": 3.961331605911255, "identity": 0.6535566449165344, "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_Contentment/28473633763f00566c15ed041814d1bc292b53df31929b40c5a856d699e1aca0.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": "28b886221c49cf445a5adf1bd3f6309efd6ad52907a72e09b71612005f0087ad", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Escribí el número en el sobre.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ab4db9ea276d52f12bf0b7e405dabb989a60dbe9b0f9d8bec2746cf8cc24fee3", "generation_seconds_batch": 14.375520672998391, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3852391242980957, "target_z": 4.031249818840858, "ce": 6.141753673553467, "genuineness": 4.306513786315918, "identity": 0.6633055210113525, "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_Contentment/28b886221c49cf445a5adf1bd3f6309efd6ad52907a72e09b71612005f0087ad.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "28c58749df040a6feb7f195c4d7f15045fd23bb65d5a1fbbfa0dd0d7166fbb2a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "5a7542eaa1e3a8d895e8cd34f269113a91f272342ecef6a09f2e09bb23dccf05", "generation_seconds_batch": 19.58508861507289, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.125462770462036, "target_z": 3.5156251756134536, "ce": 6.395919322967529, "genuineness": 4.137060642242432, "identity": 0.6089726686477661, "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_Contentment/28c58749df040a6feb7f195c4d7f15045fd23bb65d5a1fbbfa0dd0d7166fbb2a.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "297e63ff56cdb288f31a1fe8d459b28254d7a3342bc25b13e5278812b454cfc2", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bf87c1392a27c46f944d4f4289313f4ca107c3756734b52f9b999e4e5c4cf8f2", "generation_seconds_batch": 14.903395778033882, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.164822816848755, "target_z": 3.5937501072166347, "ce": 6.268836498260498, "genuineness": 3.8797430992126465, "identity": 0.27207446098327637, "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_Contentment/297e63ff56cdb288f31a1fe8d459b28254d7a3342bc25b13e5278812b454cfc2.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "298dc0bbd632a4395a530161aca79f4e0b39fcc2c30e0da4bd7131165906eecc", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f8892275804d440e6754123b7cbe7413ec7718f0b32d531e5af177fe99b5b0c9", "generation_seconds_batch": 14.43152296601329, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.43247127532959, "target_z": 4.124999926057493, "ce": 6.252951145172119, "genuineness": 4.231201171875, "identity": 0.4734644293785095, "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_Contentment/298dc0bbd632a4395a530161aca79f4e0b39fcc2c30e0da4bd7131165906eecc.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "29961801ca13a4417afbd36e59da6afaf9eabde0defbc9e2f037d7c45d14d173", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e3e41c70c8696266eca7fcda7c2bf405fc98eed3a08618b28530b99d2cbcbdb7", "generation_seconds_batch": 17.379004957037978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.574167490005493, "target_z": 4.406249774475354, "ce": 6.38003396987915, "genuineness": 4.331617832183838, "identity": 0.2799050807952881, "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_Contentment/29961801ca13a4417afbd36e59da6afaf9eabde0defbc9e2f037d7c45d14d173.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": "29cc67d31da047af099f1558bc4b8e1e011115bc44034558a428171b3dcc06c9", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "edafd6a16cbce9e82bda1125d478156c111670691761d66eda8abc1bc183d23f", "generation_seconds_batch": 19.24625567905605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9601503610610962, "target_z": 3.1875000369712536, "ce": 6.141753673553467, "genuineness": 4.432034492492676, "identity": 0.7297057509422302, "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_Contentment/29cc67d31da047af099f1558bc4b8e1e011115bc44034558a428171b3dcc06c9.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "29f54a99cd7abde9b3097c67a18d1314d1522425d3615b1af7cb364b98ebac17", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "7440403e18a6dd569f193bf953503a42030878b830ed3c15b94c8fa7cf97cae3", "generation_seconds_batch": 14.495979923987761, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.101846694946289, "target_z": 3.468750122005136, "ce": 6.0146708488464355, "genuineness": 4.005263805389404, "identity": 0.4865052103996277, "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_Contentment/29f54a99cd7abde9b3097c67a18d1314d1522425d3615b1af7cb364b98ebac17.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": "2aa99116c5257d7708176c5c6e75b5af01cd651fb11ce2d263595ac61933d04d", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The road turns left behind the bridge.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f66418d541431f7d49eb65c166f4591850ff101e019d0e65e3078a59f6346213", "generation_seconds_batch": 14.682357870973647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.235671043395996, "target_z": 3.734375268041587, "ce": 6.483288764953613, "genuineness": 4.042920112609863, "identity": 0.24331781268119812, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/2aa99116c5257d7708176c5c6e75b5af01cd651fb11ce2d263595ac61933d04d.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "2b271ab933a020374de252d31481511d3eff30451afa8dda742fc0857e38e5c0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2318b2130359e2ee503c7723bb31cc54ac747c9fc1de8e01a7a14cbe57077e2c", "generation_seconds_batch": 20.98695431498345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3380072116851807, "target_z": 3.937500184856267, "ce": 6.3641486167907715, "genuineness": 4.005263805389404, "identity": 0.2630666494369507, "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_Contentment/2b271ab933a020374de252d31481511d3eff30451afa8dda742fc0857e38e5c0.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": "2b3753ac418fde8cb13dbd0371fb42e6da01ed960e1e60441f89b15273a891a4", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f69e65f550d99ee09046f2e2d4aef0e844008be3e8d7c1b51785c9f44a10df81", "generation_seconds_batch": 19.263845068984665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.030998468399048, "target_z": 3.3281249611801837, "ce": 6.221180438995361, "genuineness": 4.093128204345703, "identity": 0.6633509397506714, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunchen 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_Contentment/2b3753ac418fde8cb13dbd0371fb42e6da01ed960e1e60441f89b15273a891a4.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "2b8124ac8d06452138928dd4c46e9a49748478865ffd6753015f17e8cb4ca318", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b8a41f1ef5df2817a2f03c755dd1c14d00ef9bb0bb05df6dd8a4b0e043629d6f", "generation_seconds_batch": 20.221746916067787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.078230619430542, "target_z": 3.421875068396819, "ce": 6.332377910614014, "genuineness": 4.369274139404297, "identity": 0.6090226173400879, "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_Contentment/2b8124ac8d06452138928dd4c46e9a49748478865ffd6753015f17e8cb4ca318.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "2bb9f80f3ab326c73f7079b9abefbed37226ce7eb516cd7efe86747c7abf557e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "3906437020020feba2f36a21c7e51eb805933f80e2dad5df9693402e604b7734", "generation_seconds_batch": 14.492652300046757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6056556701660156, "target_z": 4.468750003697125, "ce": 6.0305562019348145, "genuineness": 4.030367851257324, "identity": 0.71448814868927, "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_Contentment/2bb9f80f3ab326c73f7079b9abefbed37226ce7eb516cd7efe86747c7abf557e.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "2bba0c775ed3f05e8beebe1fccf315e56fca22cde8ebff06e950cf6ab91a8bd1", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d2493624c713269fb53b9c53ca0f313228818268f2994533bbd83ca0adb085d1", "generation_seconds_batch": 14.427359698922373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.43247127532959, "target_z": 4.124999926057493, "ce": 6.046441555023193, "genuineness": 4.036643981933594, "identity": 0.4297528862953186, "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_Contentment/2bba0c775ed3f05e8beebe1fccf315e56fca22cde8ebff06e950cf6ab91a8bd1.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": "2bc5549c3973fef1ffdbedbae80df2ba2f282ad6c3f1e73607ce87a166afc6d9", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e1e105585068a4d89e0b9776e5e87c0654fd7582328b1b687be17a55126468d3", "generation_seconds_batch": 19.287631756975316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.526935577392578, "target_z": 4.312500140490763, "ce": 6.157639026641846, "genuineness": 4.3881025314331055, "identity": 0.7540238499641418, "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_Contentment/2bc5549c3973fef1ffdbedbae80df2ba2f282ad6c3f1e73607ce87a166afc6d9.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "2c4c1f7c619ca41b9d57b2fae9765c9317c1db4dd1b192dc6549ac5ab12f550e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "4e6f079cc19a41b71e5b1840c7f93c9567831051f0c13e7d73ca62a8526a7852", "generation_seconds_batch": 19.77457990392577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4482152462005615, "target_z": 4.156249804052357, "ce": 5.855817794799805, "genuineness": 3.8044304847717285, "identity": 0.5425024032592773, "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_Contentment/2c4c1f7c619ca41b9d57b2fae9765c9317c1db4dd1b192dc6549ac5ab12f550e.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "2c6fd6e26bc2e382dce66c02682678288bc2caaa391dbce244973812fe948dc1", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "43d061bc15202df009080d92b182616871efee0e6e2ba038342a400019b8da97", "generation_seconds_batch": 14.480917745037004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.802709937095642, "target_z": 2.874999837326485, "ce": 6.038498878479004, "genuineness": 4.337893962860107, "identity": 0.37538713216781616, "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_Contentment/2c6fd6e26bc2e382dce66c02682678288bc2caaa391dbce244973812fe948dc1.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "2cd8ac302fc6907f9b8f441cb1e636b3f2d795165caf9452ac4d723e069c17e8", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7161589e828b400598528098ac9664a402dc5cb4b364b48a4866f1804e3efe33", "generation_seconds_batch": 20.008611661032774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.54267954826355, "target_z": 4.343750018485626, "ce": 6.1894097328186035, "genuineness": 4.469690799713135, "identity": 0.8111520409584045, "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_Contentment/2cd8ac302fc6907f9b8f441cb1e636b3f2d795165caf9452ac4d723e069c17e8.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "2cfb389ff7b53629d9662f4d9e74eb33cee4211d03f1b68b4fe518b21be115e6", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "8575e1a0e9d81a272468416ddaee066e40d8ee9f3cbcbedbd001923dce269f8f", "generation_seconds_batch": 19.929894761997275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.188438892364502, "target_z": 3.6406251608249525, "ce": 6.316492557525635, "genuineness": 3.9550557136535645, "identity": 0.44456130266189575, "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_Contentment/2cfb389ff7b53629d9662f4d9e74eb33cee4211d03f1b68b4fe518b21be115e6.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "2d2372646a03271af97e88826a7a3467f256bc4b9893253ddbf49fa717a0c5f9", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "396106166ab53187f93d5eec228cd1d4bbfe01bcad38acf8f6ccb812ea9ac1db", "generation_seconds_batch": 19.696284055011347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.282902956008911, "target_z": 3.8281249020261785, "ce": 6.2767791748046875, "genuineness": 3.9927117824554443, "identity": 0.3099604547023773, "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_Contentment/2d2372646a03271af97e88826a7a3467f256bc4b9893253ddbf49fa717a0c5f9.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "2d5450baddb01caffa91e95a0521c7713d029f63d54ffd22ba049ae7895ce316", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "3920f9396fc0aeb364a2efa9dfb88d9126a2e02d041d174117412425c5b81a3f", "generation_seconds_batch": 19.78508611698635, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3537511825561523, "target_z": 3.968750062851131, "ce": 6.1894097328186035, "genuineness": 3.6349775791168213, "identity": 0.29424965381622314, "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_Contentment/2d5450baddb01caffa91e95a0521c7713d029f63d54ffd22ba049ae7895ce316.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "2d5ac1f5992489cc4070b2e0a99eb2e95495666fb0b820a2b6fece19a87834f4", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "fe8682750013100e859a9ecf204d924d80772c3dd51ee9e135a44fe962faa7c8", "generation_seconds_batch": 23.683720311964862, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.141206741333008, "target_z": 3.5468750536083173, "ce": 6.395919322967529, "genuineness": 4.162164688110352, "identity": 0.6291185617446899, "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_Contentment/2d5ac1f5992489cc4070b2e0a99eb2e95495666fb0b820a2b6fece19a87834f4.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "2d9065ea54f928fdabf98cbcf1f1f89b2fe573e59eaa8dca39c141fa47b1db84", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "30ccab694d279e0caf280f49860306d266d58d0db1da729e912e981d31f26149", "generation_seconds_batch": 19.687784363981336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3852391242980957, "target_z": 4.031249818840858, "ce": 6.268836498260498, "genuineness": 4.3127899169921875, "identity": 0.5145663619041443, "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_Contentment/2d9065ea54f928fdabf98cbcf1f1f89b2fe573e59eaa8dca39c141fa47b1db84.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "2dc9f3b374b61673477e786693d583f27110f8929d0898b3977e051ef6d61c63", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "37df4436813e136052026c45b4c6e9ee2649efc268d6ec8cdbfb42c47440e8f4", "generation_seconds_batch": 19.601129529997706, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.747351884841919, "target_z": 4.749999852114986, "ce": 6.252951145172119, "genuineness": 3.6224255561828613, "identity": 0.3907335102558136, "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_Contentment/2dc9f3b374b61673477e786693d583f27110f8929d0898b3977e051ef6d61c63.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "2df4f1888f0fea5d17d845e5e85000e1398908662820dde6d605800b57dec8d0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "68c6fdbc6607e541bcc5b5dfd731b9eb47cd2276d710c8824b501684dcb614b1", "generation_seconds_batch": 19.18508251500316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7397338151931763, "target_z": 2.7499998521149864, "ce": 6.205295085906982, "genuineness": 4.432034492492676, "identity": 0.6820073127746582, "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_Contentment/2df4f1888f0fea5d17d845e5e85000e1398908662820dde6d605800b57dec8d0.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "2e0d4c8822e30aebe5992eae2b6151c19d8e1675e7a215869584d9b4c4226fce", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "6692c516d2c74d9b0589a53fdadd4a8add8a31aad5dc3d06917dbc0212328729", "generation_seconds_batch": 19.53361879696604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.054614543914795, "target_z": 3.3750000147885015, "ce": 6.3641486167907715, "genuineness": 3.973883628845215, "identity": 0.509882926940918, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschaffen.", "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_Contentment/2e0d4c8822e30aebe5992eae2b6151c19d8e1675e7a215869584d9b4c4226fce.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": "2e38c5dccbf0172f900fca882390797be9f2439fb4cdca39d449887684083ae9", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "9bea13a800fcfcf403f4a072255fecb7f12614f54846f8f6a2186d8c520c06b8", "generation_seconds_batch": 14.597186562954448, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1805667877197266, "target_z": 3.6249999852114985, "ce": 6.332377910614014, "genuineness": 4.262581825256348, "identity": 0.5241029262542725, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich laß sie zweimal, dann legte ich das Handy weg, sag mir, wann wir reden können.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/2e38c5dccbf0172f900fca882390797be9f2439fb4cdca39d449887684083ae9.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "2e9412a27dfc0e110b892f4c7e6b6ccd5a1b47ed1ca5995ae4c1cd8e953edcc0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "1b2006208da6a3b3560072afaec5a67f9d6adeae61310ec5da76ffa369014426", "generation_seconds_batch": 20.860198891023174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6137815713882446, "target_z": 2.499999881691989, "ce": 6.173524379730225, "genuineness": 4.243753433227539, "identity": 0.6531387567520142, "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_Contentment/2e9412a27dfc0e110b892f4c7e6b6ccd5a1b47ed1ca5995ae4c1cd8e953edcc0.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "2ec2d67351dad82fd1ee13ced4429d77f234664419abe13e326b716dc46e968c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "ca348c939bbd7ffc7e928788b7743572f38a943943cb3167d88903ea5116e14d", "generation_seconds_batch": 16.395434860954992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1175906658172607, "target_z": 3.5, "ce": 6.38797664642334, "genuineness": 4.325342178344727, "identity": 0.5655267834663391, "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_Contentment/2ec2d67351dad82fd1ee13ced4429d77f234664419abe13e326b716dc46e968c.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "2f9dd9bc2a7837249c260006f482773bbb8bbaea6fb4cc2354bd976aab6422d5", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "540e6095b2bca9b8df007befcb2bbb3498cd3e8183d1417c00e16ff92b3c00f0", "generation_seconds_batch": 20.583765798946843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.43247127532959, "target_z": 4.124999926057493, "ce": 6.395919322967529, "genuineness": 4.582659721374512, "identity": 0.791753888130188, "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_Contentment/2f9dd9bc2a7837249c260006f482773bbb8bbaea6fb4cc2354bd976aab6422d5.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "2fb3ddc8a853c00ee306e9225fbbee94b1e25d29dfaf9ae9b8703010825050e2", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "4c9dbfe8bf4b430535ac7393c2ff6349cfe557de5f1e8aec1c57d1d4730320fe", "generation_seconds_batch": 14.713354922016151, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.101846694946289, "target_z": 3.468750122005136, "ce": 6.086154937744141, "genuineness": 4.124508857727051, "identity": 0.564702033996582, "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_Contentment/2fb3ddc8a853c00ee306e9225fbbee94b1e25d29dfaf9ae9b8703010825050e2.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "2fd1d6cd06560355f4536b5afcedd8670bfe80eeda79aad02aee8500a8127f40", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "9e9c74149a63177fe7241724cd66ccf253b65793e98dd56b80ea81edd4e5b194", "generation_seconds_batch": 14.30923743499443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.912918210029602, "target_z": 3.0937499297546185, "ce": 6.221180438995361, "genuineness": 4.15588903427124, "identity": 0.5483824610710144, "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_Contentment/2fd1d6cd06560355f4536b5afcedd8670bfe80eeda79aad02aee8500a8127f40.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "2fe16a0d774c4c1e868a2e3b37395298e7abf9f7312762df9aa0337846198203", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4e516d18ac08863835da054e61cec91d55f974cdbfbd383cdc2b53003898a308", "generation_seconds_batch": 19.220774019951932, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.259286880493164, "target_z": 3.781249848417861, "ce": 6.149696350097656, "genuineness": 4.243753433227539, "identity": 0.6820025444030762, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/2fe16a0d774c4c1e868a2e3b37395298e7abf9f7312762df9aa0337846198203.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "2fe5adde73aa1535d5c0c929dbc6cb7065ee172f2050917e2b067e9336dced66", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "c1d32d37538109b552ee6e55455bc2a73e33af0a509a0444b1c77cf9249c1bfd", "generation_seconds_batch": 20.397297626012005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6056556701660156, "target_z": 4.468750003697125, "ce": 6.197352409362793, "genuineness": 4.287685871124268, "identity": 0.6675466299057007, "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_Contentment/2fe5adde73aa1535d5c0c929dbc6cb7065ee172f2050917e2b067e9336dced66.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "303203dfa234608ade4305f45d24c27e21d17f48fb2e6332e13b53b131748b0b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2684736c63b8b83cbdc15743bc66a1c8861f56a78ba598d23ac53414f131a528", "generation_seconds_batch": 21.953701136983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.298647165298462, "target_z": 3.8593752532530856, "ce": 6.221180438995361, "genuineness": 3.9299514293670654, "identity": 0.3039035201072693, "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_Contentment/303203dfa234608ade4305f45d24c27e21d17f48fb2e6332e13b53b131748b0b.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "307f3712e0a7e7f387524034dc7bdb1556eb3e3ee7bf8538ae73b5f9db3e6c89", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2ce3a70b4f0f1ce712224b5a215d9bb3ac2043ab18e168978c1db35728cee49f", "generation_seconds_batch": 20.03565426694695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.101846694946289, "target_z": 3.468750122005136, "ce": 6.316492557525635, "genuineness": 4.532451152801514, "identity": 0.6405709981918335, "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_Contentment/307f3712e0a7e7f387524034dc7bdb1556eb3e3ee7bf8538ae73b5f9db3e6c89.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "310e0ed69fc80e61c3ba4fc576a8e666c8862519fb1628ef221baccbc9525dc5", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "97d7e69f4fa45576dea72e16c33c94c6849cee97b3e70c108c83b3cffb917f85", "generation_seconds_batch": 21.643775925040245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.101846694946289, "target_z": 3.468750122005136, "ce": 6.340320587158203, "genuineness": 4.344170093536377, "identity": 0.5227258205413818, "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_Contentment/310e0ed69fc80e61c3ba4fc576a8e666c8862519fb1628ef221baccbc9525dc5.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "3143896e906bd7039bb48c2f4986d7ecde43e40b298ddfffa6a04325d6139a58", "bucket": "emo_Contentment", "phase": "wording", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "4faf558f300d1b6e537416d7a1a8906341a851d70843b637ee5aedd42a65b1df", "generation_seconds_batch": 15.48966299497988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.141460657119751, "target_z": 1.5624999926057492, "ce": 6.1894097328186035, "genuineness": 4.419482707977295, "identity": 0.7708563804626465, "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_Contentment/3143896e906bd7039bb48c2f4986d7ecde43e40b298ddfffa6a04325d6139a58.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "317e068816a77528efc5fcb99f27088f2a9be69ef26b9da7a5d72f696aa3c29d", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "5cea6d82bff9291248ce5c91bdb6d9458b5f19c82ef0931e21e2776802264bb6", "generation_seconds_batch": 14.94908744795248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1569507122039795, "target_z": 3.578124931603181, "ce": 6.213237762451172, "genuineness": 4.293961524963379, "identity": 0.7451419830322266, "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_Contentment/317e068816a77528efc5fcb99f27088f2a9be69ef26b9da7a5d72f696aa3c29d.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": "31861beab9d59f6cd13943c57de2219a0fa805229b08a63bd3d97946c25cb2f0", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I wrote the number on the envelope.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c692a02856377dbb3de42d94c292c0bbbe9a28b3f896948717456c65cec75cfc", "generation_seconds_batch": 14.600105297053233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3380072116851807, "target_z": 3.937500184856267, "ce": 6.419747352600098, "genuineness": 4.268857479095459, "identity": 0.19524067640304565, "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_Contentment/31861beab9d59f6cd13943c57de2219a0fa805229b08a63bd3d97946c25cb2f0.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "31ba2fb75b3428944b9ae47feaa4ce81c4909f6335cd132f224059b07cde3348", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "5a4a622149f1c99aaf56ab593bfc5758ce48d1c94c493fe5edcb29c59c0f66b7", "generation_seconds_batch": 14.527432237984613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.306519031524658, "target_z": 3.874999955634496, "ce": 6.125868320465088, "genuineness": 4.356721878051758, "identity": 0.5891538262367249, "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_Contentment/31ba2fb75b3428944b9ae47feaa4ce81c4909f6335cd132f224059b07cde3348.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": "31e2e9755a376cceabe919b035bf1e9c6fc714b9bef7e33fe25bce6b14fa06a1", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e949ac0fc2341623833d5d274eefcf17dc2d3e3ad2920439dbc191a821afd8c2", "generation_seconds_batch": 14.722495881957002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.259286880493164, "target_z": 3.781249848417861, "ce": 6.181467056274414, "genuineness": 4.268857479095459, "identity": 0.7451456189155579, "hypothesis": "Quelqu'un n'a déplacé la petite chaise bleue. Elle était ici. Près de la grande bibliothèque, nous la remettrons après le déjeuner.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/31e2e9755a376cceabe919b035bf1e9c6fc714b9bef7e33fe25bce6b14fa06a1.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "31f8d33e154b7311308080ed0d69777156a000598f7a97dc82f524be9987cfaa", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "4856e8dc19b20f37a36bb00c0fd2957db819cc026c7082ffcbbd74abe67fbc4a", "generation_seconds_batch": 19.220774019951932, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.32226300239563, "target_z": 3.9062498336293596, "ce": 6.213237762451172, "genuineness": 4.1998209953308105, "identity": 0.5763876438140869, "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_Contentment/31f8d33e154b7311308080ed0d69777156a000598f7a97dc82f524be9987cfaa.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "327f8d77b2f0abe709a91fadd14e6d7b3720940e108ee8a62c238321837386be", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a0930ffdbfec04381da3f21e9200589f102f51ad3cbe201684248eb705bb7d29", "generation_seconds_batch": 23.101523864082992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.479703426361084, "target_z": 4.218750033274128, "ce": 6.173524379730225, "genuineness": 4.256305694580078, "identity": 0.6225712895393372, "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_Contentment/327f8d77b2f0abe709a91fadd14e6d7b3720940e108ee8a62c238321837386be.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "32de42ca707baf4eeed5a9ac02329a0749cec0b8ac0941a188a0b8f828b62c93", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e3eaf6acb53e02e6e52ee30a64f90623ec8c09ef1d76a772468474e3af0ffb2f", "generation_seconds_batch": 20.406746561056934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.598037600517273, "target_z": 2.4687500036971253, "ce": 5.982900142669678, "genuineness": 4.287685871124268, "identity": 0.7943532466888428, "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_Contentment/32de42ca707baf4eeed5a9ac02329a0749cec0b8ac0941a188a0b8f828b62c93.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "338ce299a828890f8378b231c9a1436ded150f188f48043beeb021886f8dbe38", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "313355398fef04190ece35dc0a0e059e2d57519401927c227913d446a0639f19", "generation_seconds_batch": 14.480917745037004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9286623001098633, "target_z": 3.125000044365504, "ce": 6.340320587158203, "genuineness": 4.494794845581055, "identity": 0.37566012144088745, "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_Contentment/338ce299a828890f8378b231c9a1436ded150f188f48043beeb021886f8dbe38.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "33d886168db1a65dd27360efff1d699e37754eef03081464738b372bc2787e50", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "10b658114a758e334f099e0d3049fd0a1f1b51ad2c079b9a5c225eee5cb58c36", "generation_seconds_batch": 20.860198891023174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1097185611724854, "target_z": 3.4843748243865464, "ce": 6.229123115539551, "genuineness": 4.2374773025512695, "identity": 0.42533421516418457, "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_Contentment/33d886168db1a65dd27360efff1d699e37754eef03081464738b372bc2787e50.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "79a12f14a84e9fdc9b90fc360d5dba5c97e28c7b5d6603accd63afa7bb134834", "generation_seconds_batch": 14.363232800038531, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9050462245941162, "target_z": 3.078124990757187, "ce": 6.078212261199951, "genuineness": 4.507347106933594, "identity": 0.48502111434936523, "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_Contentment/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "3415b3952bdd17f00665a0cee8d8f82fbbb26d1f53559f335ae300e1b95da7f8", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2f043a5f51ab43971086c5251ea5a36595f2b794994d2bceb1a433d55fc87ccf", "generation_seconds_batch": 19.602233020938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2435429096221924, "target_z": 3.7499999704229974, "ce": 5.982900142669678, "genuineness": 3.898571252822876, "identity": 0.26750439405441284, "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_Contentment/3415b3952bdd17f00665a0cee8d8f82fbbb26d1f53559f335ae300e1b95da7f8.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": "346a9f0d036f9bbdab6b0fc7b3b47d900eb715a2fe01b1447a55ced9aae4b0e7", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cdd443df081d6215697bcdb054f3fd135b851c9ceadc7d25cbcd1602870949a8", "generation_seconds_batch": 21.79814751003869, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.912918210029602, "target_z": 3.0937499297546185, "ce": 6.149696350097656, "genuineness": 4.262581825256348, "identity": 0.5766387581825256, "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_Contentment/346a9f0d036f9bbdab6b0fc7b3b47d900eb715a2fe01b1447a55ced9aae4b0e7.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "466ecf7cda79bc39061e2df6006069c2f4008122b543a0cfd3890e7cde412aba", "generation_seconds_batch": 14.459670276963152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8735581636428833, "target_z": 3.0156249981514374, "ce": 6.4515180587768555, "genuineness": 4.061748504638672, "identity": 0.3520347476005554, "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_Contentment/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "347f1c5b4b50e043c46acff8059dfdcaccfe58cef3acac18a5c100bb734bd47e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f7f879279d888875c0947029080f5e61bc54558dd0c87c7bf3498b1bf9e5535b", "generation_seconds_batch": 20.250623031985015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7318618297576904, "target_z": 2.7343749131175543, "ce": 6.141753673553467, "genuineness": 4.243753433227539, "identity": 0.46106642484664917, "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_Contentment/347f1c5b4b50e043c46acff8059dfdcaccfe58cef3acac18a5c100bb734bd47e.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "3520b7638f4723624a0b8f12d92bc0cecbcb8f44d9737a5bd6a75937924a6c2e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "54b01c892f355566b6ce31e64776904d06a6a5044ddb00c706e0847e9dfddf32", "generation_seconds_batch": 14.298114493954927, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6610137224197388, "target_z": 2.593749988908624, "ce": 6.221180438995361, "genuineness": 4.545003414154053, "identity": 0.6340545415878296, "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_Contentment/3520b7638f4723624a0b8f12d92bc0cecbcb8f44d9737a5bd6a75937924a6c2e.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": "352b07adfcc5b767102d19e4ee2ea531f8e59ad34e69e15ecd53d64f446b607a", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2de4f61f30e0138852b5b7ac031b8966ceb6f3959778a3e227f0a08f65169ffa", "generation_seconds_batch": 14.387369683012366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.259286880493164, "target_z": 3.781249848417861, "ce": 6.300607204437256, "genuineness": 4.137060642242432, "identity": 0.7112302780151367, "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_Contentment/352b07adfcc5b767102d19e4ee2ea531f8e59ad34e69e15ecd53d64f446b607a.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "355d62c6675b122d1e45373ab301fcad9f64409698ff544e46a8c9c37617ed32", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "c51e63790aab704adfc9105296dbcb33244ffa92d4764cbeadb63ce65316508a", "generation_seconds_batch": 19.811674798023887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3380072116851807, "target_z": 3.937500184856267, "ce": 6.149696350097656, "genuineness": 4.375550270080566, "identity": 0.6862807869911194, "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_Contentment/355d62c6675b122d1e45373ab301fcad9f64409698ff544e46a8c9c37617ed32.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "3580b5c080188fb781d9ab2719fc1297ec6a037bd4d6323ace91c92bfe2dfb0a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "fbcd7f1500e89fe27ad71b139a58376bcc572596c4bcf040feb37bc626752707", "generation_seconds_batch": 19.965466755907983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6686317920684814, "target_z": 4.593749988908624, "ce": 6.316492557525635, "genuineness": 4.344170093536377, "identity": 0.3898012936115265, "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_Contentment/3580b5c080188fb781d9ab2719fc1297ec6a037bd4d6323ace91c92bfe2dfb0a.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "35946c54500c0a2228bafb71789ef9b9850b388cc06d177e2025c639b6dc7475", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "9d8f2fe05ee63caa479584673ecb684d62032b5d2807f5ddc31b02fd7ee15c09", "generation_seconds_batch": 19.846119016990997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.275031089782715, "target_z": 3.8125001996447683, "ce": 6.181467056274414, "genuineness": 4.137060642242432, "identity": 0.5309553742408752, "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_Contentment/35946c54500c0a2228bafb71789ef9b9850b388cc06d177e2025c639b6dc7475.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "35ec57a7f5941207d26251e5f55b28607dd54f2e31f0b27fb3cffd6096e13370", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "92e1efeb55e3110a9a965db418c49bf19768069b777a2ed1b1e064da2ef1468a", "generation_seconds_batch": 20.345622310996987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.282902956008911, "target_z": 3.8281249020261785, "ce": 6.252951145172119, "genuineness": 3.9676074981689453, "identity": 0.3209189772605896, "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_Contentment/35ec57a7f5941207d26251e5f55b28607dd54f2e31f0b27fb3cffd6096e13370.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "35f4da96f2d6ca55ae7895d0cf08f0d3ca62518a4ce69f701a4f33ea24d48a63", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "60cb5512484b1b1062ffc6e431e453ef012f6e46df32ce70c090f60a5ae8e26d", "generation_seconds_batch": 22.640119376941584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.282902956008911, "target_z": 3.8281249020261785, "ce": 6.348263263702393, "genuineness": 4.011539936065674, "identity": 0.45118921995162964, "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_Contentment/35f4da96f2d6ca55ae7895d0cf08f0d3ca62518a4ce69f701a4f33ea24d48a63.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": "3637818433766932921d1212e3a19147967e7c884b74eb87a8fe6013b2203177", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fdf8c367b5eb81e4d331f798197f60209b2742d1c66d28fd0674b3b309f03297", "generation_seconds_batch": 14.387369683012366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.212054967880249, "target_z": 3.68750021443327, "ce": 6.141753673553467, "genuineness": 4.099404335021973, "identity": 0.6967322826385498, "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_Contentment/3637818433766932921d1212e3a19147967e7c884b74eb87a8fe6013b2203177.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": "3683ce90a0aaedc03169b1dc5733b4760918c63af2df65d7288bbe8aaf49a8d9", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "feaf3af809f85730f2f75278a0f93a3eb0259dd78309c77dda9ba1e964e613df", "generation_seconds_batch": 19.222941415035166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.149078845977783, "target_z": 3.562500229221771, "ce": 6.3641486167907715, "genuineness": 4.331617832183838, "identity": 0.46960243582725525, "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_Contentment/3683ce90a0aaedc03169b1dc5733b4760918c63af2df65d7288bbe8aaf49a8d9.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": "369f1552777fe741759a13f8a29acb49443feb355cfe18333579e74d6f1d5d15", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b9b5cfd045dfe795242c7fba9511065b7aae52ea32648e2724bb0d42060c452c", "generation_seconds_batch": 14.449652798939496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9992563724517822, "target_z": 5.249999792960981, "ce": 6.308549880981445, "genuineness": 4.243753433227539, "identity": 0.7202156186103821, "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_Contentment/369f1552777fe741759a13f8a29acb49443feb355cfe18333579e74d6f1d5d15.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "370179d3875df730ed28a8f14c06ec27942069c99562a86fbcfe548b194bfa14", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "0f809ed917315b16e5e90352b41d3a5fc8783589559c6eae2d041c5baa486bb8", "generation_seconds_batch": 19.45805310807191, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.43247127532959, "target_z": 4.124999926057493, "ce": 6.1020402908325195, "genuineness": 4.243753433227539, "identity": 0.6107465028762817, "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_Contentment/370179d3875df730ed28a8f14c06ec27942069c99562a86fbcfe548b194bfa14.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "37195491726c327eda29ef88280248e0763435a0c5e4c31ee19e0bf5fe54f2f3", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "20ea781cea001df63418972242294388f6e3a66378f1502bf88a116856ab1d56", "generation_seconds_batch": 19.414420333923772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3537511825561523, "target_z": 3.968750062851131, "ce": 6.252951145172119, "genuineness": 4.607763767242432, "identity": 0.42799150943756104, "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_Contentment/37195491726c327eda29ef88280248e0763435a0c5e4c31ee19e0bf5fe54f2f3.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "3751bc092c4874ad100ad5b8e417ea4c14e03141697a526600f9500a61c7a545", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "59bc63a20b0119a1fcaf77c706b579390e7d9c987b9a1b160286b584d3c1d1c9", "generation_seconds_batch": 19.210153987049125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4639594554901123, "target_z": 4.187500155279264, "ce": 6.3641486167907715, "genuineness": 3.7416701316833496, "identity": 0.31366103887557983, "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_Contentment/3751bc092c4874ad100ad5b8e417ea4c14e03141697a526600f9500a61c7a545.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "37d87259369e3d254f22c58de1f63dbee970c3473d6e115ae52b6a1478aec92a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "3d7a424e4498fc1919999e0576c39b0d0f74793d9a3cdc0fa1c5c44a688276ac", "generation_seconds_batch": 22.584256325964816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2277989387512207, "target_z": 3.7187500924281336, "ce": 6.181467056274414, "genuineness": 4.024092197418213, "identity": 0.4265122413635254, "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_Contentment/37d87259369e3d254f22c58de1f63dbee970c3473d6e115ae52b6a1478aec92a.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "37dfa539c2d0ac3f95ece129d3d55b36fc29798b41a27662ad82fd1adec0f21d", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "23f9d036cb298edc88bc35c3a65324b7c00ae5c3804796ab69a7a9fcf8c8ad3e", "generation_seconds_batch": 20.498778149019927, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3143911361694336, "target_z": 3.8906251312479494, "ce": 6.078212261199951, "genuineness": 4.2374773025512695, "identity": 0.553274393081665, "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_Contentment/37dfa539c2d0ac3f95ece129d3d55b36fc29798b41a27662ad82fd1adec0f21d.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "387218d5c8f6017816877c439d6d674e97f6c3b71d64cf7a258f96746f9aa9db", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "1f6a8e6e6f7a226d3dfd642c1e59eacbd16a2820e59418d6008007352ba2a389", "generation_seconds_batch": 21.7692374039907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.32226300239563, "target_z": 3.9062498336293596, "ce": 5.95112943649292, "genuineness": 4.319066047668457, "identity": 0.5764414668083191, "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_Contentment/387218d5c8f6017816877c439d6d674e97f6c3b71d64cf7a258f96746f9aa9db.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "388a2d81499dc6ed266c9edcfbfdbf281be361842f6ad47bbdb109b143d6b84e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "fdcfb974fbfc88cd3eee7ec2b67a7c4037334b3c0737533696be817810b84f90", "generation_seconds_batch": 19.615125727956183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2435429096221924, "target_z": 3.7499999704229974, "ce": 6.173524379730225, "genuineness": 4.413206577301025, "identity": 0.7000249624252319, "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_Contentment/388a2d81499dc6ed266c9edcfbfdbf281be361842f6ad47bbdb109b143d6b84e.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "38acbb53ec041d9434aaffed5eadd074401f1505a2394bed45fd151ff86cb1d0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "15b4909b484d6824b652457f2f7b2cd60fdd6345a6a5d3c4a2e7c8e6fd91d46d", "generation_seconds_batch": 19.883153354981914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.999510407447815, "target_z": 3.2656249685744347, "ce": 6.395919322967529, "genuineness": 4.093128204345703, "identity": 0.6243957877159119, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinführen.", "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_Contentment/38acbb53ec041d9434aaffed5eadd074401f1505a2394bed45fd151ff86cb1d0.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "394d342e64e10a308d504fa8b90882493d7af74b35483fde126b08fe228fc6ca", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "14a7c9e58ebef07807ebd7cf0fc126a314e997f4603cb76ceb490c0507e488cf", "generation_seconds_batch": 20.591204055934213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.259286880493164, "target_z": 3.781249848417861, "ce": 6.149696350097656, "genuineness": 4.337893962860107, "identity": 0.4375334084033966, "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_Contentment/394d342e64e10a308d504fa8b90882493d7af74b35483fde126b08fe228fc6ca.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "395fdc60a4f6e43a4fbd56deefb91aad87f7e37276eb255035d90af94cf0b142", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "87647389ffe381c11983b3a39b46b81e76263320a14d6014f91b829be0404bd4", "generation_seconds_batch": 19.474694291013293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5584235191345215, "target_z": 4.374999896480491, "ce": 6.332377910614014, "genuineness": 4.595211505889893, "identity": 0.8135262727737427, "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_Contentment/395fdc60a4f6e43a4fbd56deefb91aad87f7e37276eb255035d90af94cf0b142.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "3a1231b531ab8f6597e9e31fb8ea911b920895cfc0b14cf9f77a8770e386be83", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "0ae38e32b1a3a3db10e8c394afdfa2014669cc1ca7c44ac4ecc6af33ac4d9628", "generation_seconds_batch": 20.394868689007126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4248532056808472, "target_z": 2.124999926057493, "ce": 6.133810997009277, "genuineness": 4.306513786315918, "identity": 0.6401804685592651, "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_Contentment/3a1231b531ab8f6597e9e31fb8ea911b920895cfc0b14cf9f77a8770e386be83.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "3a13a8bb92879f659b63ffe69539646dfeb7e21b1860b326bcc8eb87f672eb46", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d0a63899e59dfc6b22f1e69b0be12d8e5f2aa712c64636f35b11f54143f8f566", "generation_seconds_batch": 14.325527510023676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5584235191345215, "target_z": 4.374999896480491, "ce": 5.927301406860352, "genuineness": 3.898571252822876, "identity": 0.43242642283439636, "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_Contentment/3a13a8bb92879f659b63ffe69539646dfeb7e21b1860b326bcc8eb87f672eb46.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": "3a3e07004d0704dcd131f0a704525e9ad0feeea79d4504869ad88fcc6755ead2", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eaf4921e184dc4c9c999e924eefc90d68fe548f5edfc152c794ae8906ec54517", "generation_seconds_batch": 14.467049314989708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.212054967880249, "target_z": 3.68750021443327, "ce": 6.284721851348877, "genuineness": 3.898571252822876, "identity": 0.3571750521659851, "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_Contentment/3a3e07004d0704dcd131f0a704525e9ad0feeea79d4504869ad88fcc6755ead2.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "3a9ba57dbe6276983a537bab721653e800f742a40c151353f1007add2d397f55", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "178af4f42c3f7777478a600b19de5804314e8232d74d16d34b788a5fd2685a38", "generation_seconds_batch": 19.94228988199029, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7316079139709473, "target_z": 4.718749974120122, "ce": 6.38797664642334, "genuineness": 4.432034492492676, "identity": 0.7117063999176025, "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_Contentment/3a9ba57dbe6276983a537bab721653e800f742a40c151353f1007add2d397f55.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "3abd97ba1f3f3f5922b0b8b05c3cea325bd498f0e8a78ff625baaaa594deb86d", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e08245f654b1e4c6eaa06c5ac4f8b344f2e4c4f97461c52664cb25acea172efc", "generation_seconds_batch": 19.549096547998488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4954473972320557, "target_z": 4.249999911268992, "ce": 6.221180438995361, "genuineness": 4.394378662109375, "identity": 0.7988585829734802, "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_Contentment/3abd97ba1f3f3f5922b0b8b05c3cea325bd498f0e8a78ff625baaaa594deb86d.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "3abe8e998b48540ba447f6117f125b1d6dce67a078cb9f62b3a55d12bc95802f", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b72d51c031132e3cdc8a14a4652f71a94ef4a7e26328b681bc567f51bf5c695b", "generation_seconds_batch": 16.076387881068513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.32226300239563, "target_z": 3.9062498336293596, "ce": 6.435632705688477, "genuineness": 4.482243061065674, "identity": 0.6490442752838135, "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_Contentment/3abe8e998b48540ba447f6117f125b1d6dce67a078cb9f62b3a55d12bc95802f.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "3b0c74f2b8f1a7d8a4ce71f10276e2f28d82fa66da1714a8258e046843284335", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "0735458e092fbaff802e08f4c6cf058839d7e1d7c53e61ab59faa059759db7d7", "generation_seconds_batch": 19.77457990392577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.298647165298462, "target_z": 3.8593752532530856, "ce": 5.808161735534668, "genuineness": 4.149612903594971, "identity": 0.5046484470367432, "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_Contentment/3b0c74f2b8f1a7d8a4ce71f10276e2f28d82fa66da1714a8258e046843284335.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "3b471a1d6346b042183772a4e01ba3d6976d2c6c7d19d62b48cef70df37b6d9e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "230e017be98e238ae566a9611d2e9f866dd800805090fcc11ff5a2f41ed42f07", "generation_seconds_batch": 14.325527510023676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.259286880493164, "target_z": 3.781249848417861, "ce": 5.839932441711426, "genuineness": 4.243753433227539, "identity": 0.5763309001922607, "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_Contentment/3b471a1d6346b042183772a4e01ba3d6976d2c6c7d19d62b48cef70df37b6d9e.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "3b49c082a2171dfca1ed74e8e0754cee4f9f0b11fab6216c6226cc6ba36e5c88", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "7e7511d78b9aa7d3fbd7d66829c193ee681d7a9ff6bd2637cb6ec6fe14207f28", "generation_seconds_batch": 14.488189007970504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4482152462005615, "target_z": 4.156249804052357, "ce": 6.197352409362793, "genuineness": 4.256305694580078, "identity": 0.7841523885726929, "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_Contentment/3b49c082a2171dfca1ed74e8e0754cee4f9f0b11fab6216c6226cc6ba36e5c88.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "3b838cdcda0a5aa73c1cec4a4b3857af796032449ebe71f6c81f6428dec9291e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3ccac6ba16e398e661fe7f5efd508aad6b7972419342c63ad595870a474704e4", "generation_seconds_batch": 14.964102057972923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7630958557128906, "target_z": 4.78124973010985, "ce": 6.38003396987915, "genuineness": 4.331617832183838, "identity": 0.3182217478752136, "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_Contentment/3b838cdcda0a5aa73c1cec4a4b3857af796032449ebe71f6c81f6428dec9291e.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "84f4aec71ffa6c63776993522d41c6aff5bf75be879d53dd01f88d12f3e5907a", "generation_seconds_batch": 14.346648339997046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8420701026916504, "target_z": 2.953125005545688, "ce": 6.173524379730225, "genuineness": 4.381826400756836, "identity": 0.5697762966156006, "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_Contentment/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.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": "3c6b8e537f82891a3ab4f1e07e8206be6e975a8575c43d9f27e30c7afc541cd1", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b8fef4548cabe966d71c04631077722fcdae6c610b0b9072aba9baacf272dca9", "generation_seconds_batch": 19.14446932799183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.164822816848755, "target_z": 3.5937501072166347, "ce": 6.221180438995361, "genuineness": 3.8922953605651855, "identity": 0.4751321077346802, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/3c6b8e537f82891a3ab4f1e07e8206be6e975a8575c43d9f27e30c7afc541cd1.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "3cea9633f827a2a20854031d24145edb51e4dd3beda8d262ad657b1ed8c487cc", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "bdb3e0665579176d0b88e6bd0323b8ad5cd77473b5f5c8bfef05189fdf1c0a25", "generation_seconds_batch": 22.52808667300269, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1333346366882324, "target_z": 3.531249877994864, "ce": 6.372091293334961, "genuineness": 3.898571252822876, "identity": 0.15596351027488708, "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_Contentment/3cea9633f827a2a20854031d24145edb51e4dd3beda8d262ad657b1ed8c487cc.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": "3dada79ff8f61d63b2f59f680d0ed71e30dafb842d102817360dab69c8f454a5", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Escribí el número en el sobre.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "58d655a300c290cb60d0bca1259859d8aa19b538975b86216d0f3221728d4f28", "generation_seconds_batch": 19.389432864030823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.259286880493164, "target_z": 3.781249848417861, "ce": 6.23706579208374, "genuineness": 4.306513786315918, "identity": 0.6190046072006226, "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_Contentment/3dada79ff8f61d63b2f59f680d0ed71e30dafb842d102817360dab69c8f454a5.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "3e25965f19f695465a059dace92cfd9ca0cd5e3c3272b0af7e1416e9e5c496e2", "bucket": "emo_Contentment", "phase": "wording", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b4cadee559b4a88caee2814665a192cfe2218400775a71a544a16f7b5fb3da1c", "generation_seconds_batch": 15.950176565907896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.164822816848755, "target_z": 3.5937501072166347, "ce": 6.260893821716309, "genuineness": 4.143336772918701, "identity": 0.08294074237346649, "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_Contentment/3e25965f19f695465a059dace92cfd9ca0cd5e3c3272b0af7e1416e9e5c496e2.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "3e4934aa61ed582ea723aed888ab6ba6d6da96aa2db886c7abcd832910c62179", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "c1b2d379c40b0624f315978f60baac97be097a59a0638f1e681406f738f20134", "generation_seconds_batch": 16.944440977065824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.54267954826355, "target_z": 4.343750018485626, "ce": 6.229123115539551, "genuineness": 4.231201171875, "identity": 0.2935422360897064, "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_Contentment/3e4934aa61ed582ea723aed888ab6ba6d6da96aa2db886c7abcd832910c62179.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "3e61f5747c3049606132d88a0f95fb28ec003fc8e4c94718dc3ed3bf752637dd", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "30c35c759d9eb66c0133d545752bd27fa3967221e35da9fe271fcb240534a85e", "generation_seconds_batch": 14.43152296601329, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0939745903015137, "target_z": 3.4531249463916827, "ce": 6.23706579208374, "genuineness": 4.482243061065674, "identity": 0.558918297290802, "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_Contentment/3e61f5747c3049606132d88a0f95fb28ec003fc8e4c94718dc3ed3bf752637dd.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": "3e841277ec93436900465b901070355583578f3fdce422e6b89cc50e6ff3a011", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "82aa0266c7aaa65b71474d990b974db515669a2746522477b4a37f4c3a7cfd2f", "generation_seconds_batch": 14.607252871035598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0703585147857666, "target_z": 3.4062498927833653, "ce": 6.372091293334961, "genuineness": 4.482243061065674, "identity": 0.5973162651062012, "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_Contentment/3e841277ec93436900465b901070355583578f3fdce422e6b89cc50e6ff3a011.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "3ebf887433d881426a61f39b7ed4381b3103bcfe85b0eb3c189e2b1ce97e77f5", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f267e7e64aa0555c9cd28d5a3f00dd21c1919a7850ff4988d87a4b7b725fd2b4", "generation_seconds_batch": 20.027965874993242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.164822816848755, "target_z": 3.5937501072166347, "ce": 6.435632705688477, "genuineness": 4.2249250411987305, "identity": 0.6474680304527283, "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_Contentment/3ebf887433d881426a61f39b7ed4381b3103bcfe85b0eb3c189e2b1ce97e77f5.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "3eca477c6b9b3d1b585850d75f3cec693022062dea5b83b306128c4726f8ded5", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b79c17408ac2dc18a07fa98ae4111f47cc6705e1a1fe350e10fc88c8bd0b58b4", "generation_seconds_batch": 22.621577456011437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.369495153427124, "target_z": 3.9999999408459948, "ce": 6.316492557525635, "genuineness": 4.381826400756836, "identity": 0.6361751556396484, "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_Contentment/3eca477c6b9b3d1b585850d75f3cec693022062dea5b83b306128c4726f8ded5.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "3f32d4e17dc20525ff6a4db504334531d40430cd842138001b0de338fe4d8fa0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "35aadc22c7290790c27aab8bd2324781cb4bc2c25cd721c03cc6ff3223c1e18b", "generation_seconds_batch": 19.540189780993387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.369495153427124, "target_z": 3.9999999408459948, "ce": 6.284721851348877, "genuineness": 4.344170093536377, "identity": 0.6864599585533142, "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_Contentment/3f32d4e17dc20525ff6a4db504334531d40430cd842138001b0de338fe4d8fa0.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "3f41d681c862d2b66a7af6eee162c1ab5c1ef3b20f18ddbac8319da3c5fa5493", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "19421e8aa61681a5ba26c48e8690a0a0b9bff911c0826d338d22cb76f47089b3", "generation_seconds_batch": 16.262243852950633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1333346366882324, "target_z": 3.531249877994864, "ce": 6.046441555023193, "genuineness": 4.024092197418213, "identity": 0.5471670031547546, "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_Contentment/3f41d681c862d2b66a7af6eee162c1ab5c1ef3b20f18ddbac8319da3c5fa5493.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "3f501013e6a488cdaf45e96f34ab21639b00dfd17d3f4f5bc561893d7b16bdfa", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "adb9c0e416ea54a9747057a093eebbcb5c217b90ed66e5769dc38c7648c605fe", "generation_seconds_batch": 14.494227676070295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3537511825561523, "target_z": 3.968750062851131, "ce": 6.292664527893066, "genuineness": 4.005263805389404, "identity": 0.14720666408538818, "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_Contentment/3f501013e6a488cdaf45e96f34ab21639b00dfd17d3f4f5bc561893d7b16bdfa.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "3f8559de1c3dc04a9d07ea4b175b0366c8add342c0ebbf1bfa6000890e74de27", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "b3c5defde0e7490836bc471d32ebd01d5119ca8348e627e47fe860a6dc4e9df0", "generation_seconds_batch": 19.5383565640077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.526935577392578, "target_z": 4.312500140490763, "ce": 5.855817794799805, "genuineness": 3.71028995513916, "identity": 0.3926871418952942, "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_Contentment/3f8559de1c3dc04a9d07ea4b175b0366c8add342c0ebbf1bfa6000890e74de27.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "3fb680c0f4b394330f0a57e0ff0f71e6ffb5f36f03bfc43e9cbcf53d8435b446", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e046701c618cb729a6f23b5584b1e48bfa8fd109ee3909d358238386739c6597", "generation_seconds_batch": 20.433204947039485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.306519031524658, "target_z": 3.874999955634496, "ce": 6.173524379730225, "genuineness": 3.9550557136535645, "identity": 0.42085015773773193, "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_Contentment/3fb680c0f4b394330f0a57e0ff0f71e6ffb5f36f03bfc43e9cbcf53d8435b446.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "3fcc943b24d1669f27266917b6571a2c9dcabdaaba950ede91054d3fc5c0d89c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "938677145d22a9319402f60122a314f7c210a979dca49dc71e639fcbc45ea40a", "generation_seconds_batch": 16.944440977065824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4639594554901123, "target_z": 4.187500155279264, "ce": 6.2767791748046875, "genuineness": 4.030367851257324, "identity": 0.317348837852478, "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_Contentment/3fcc943b24d1669f27266917b6571a2c9dcabdaaba950ede91054d3fc5c0d89c.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "40347aa5f6933b0e10beb07738bad92a816f0d4ff5ca0fd9872ce3449c0167ae", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2fd54a46b67d71f73347a4b2c1a041a9286e42e35bf92d7f4585279ca12434eb", "generation_seconds_batch": 21.692667067050934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.306519031524658, "target_z": 3.874999955634496, "ce": 6.165581703186035, "genuineness": 4.381826400756836, "identity": 0.7885571718215942, "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_Contentment/40347aa5f6933b0e10beb07738bad92a816f0d4ff5ca0fd9872ce3449c0167ae.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "403b512974858da1d45785d60019c99d563e9b752277b5de40597e03aba38601", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "c153779670cd993ec628d73c3b9d5311c05d6d14587de3a219c7211ecf16bd1f", "generation_seconds_batch": 16.36724029807374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3380072116851807, "target_z": 3.937500184856267, "ce": 6.3641486167907715, "genuineness": 4.13078498840332, "identity": 0.22345168888568878, "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_Contentment/403b512974858da1d45785d60019c99d563e9b752277b5de40597e03aba38601.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "40a83c63fee53306a3bb7d2fafd96756b1d57a204c890d45300ff268002fcdb3", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "1f76e6066abc03baa42224c86f4eebbea6d50503125cac6aec863377cadf3237", "generation_seconds_batch": 23.161915789009072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6056556701660156, "target_z": 4.468750003697125, "ce": 6.213237762451172, "genuineness": 4.18099308013916, "identity": 0.3365013599395752, "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_Contentment/40a83c63fee53306a3bb7d2fafd96756b1d57a204c890d45300ff268002fcdb3.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "40ef1c087ea4f7011715aea66efcd0d1b7f939669a5d7e3601fdaa2d89755199", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "49ec3ec45d6095ce029c0656cfcd72496a7afc9a15618bf24b70afb85493756c", "generation_seconds_batch": 19.691007470013574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4009833335876465, "target_z": 4.062500170067765, "ce": 5.855817794799805, "genuineness": 4.055472373962402, "identity": 0.5901815891265869, "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_Contentment/40ef1c087ea4f7011715aea66efcd0d1b7f939669a5d7e3601fdaa2d89755199.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "4115b576fb66d2c05850d078ab846110a071e3297a21ef937f5bc2bfcc737a28", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "5390a57d43012a850eca56dcd708465546c87af26dcf70a17ddc52c3e448d279", "generation_seconds_batch": 20.167380071012303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0861027240753174, "target_z": 3.4375002440102724, "ce": 6.1894097328186035, "genuineness": 4.375550270080566, "identity": 0.4285544753074646, "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_Contentment/4115b576fb66d2c05850d078ab846110a071e3297a21ef937f5bc2bfcc737a28.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "41333e1cf245f844de2c1f24fdb45f1e9d184d196ef65111a47b1c48fa1f0a02", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "9204642739a81f861c5d54ca39818ad00394f12ef93ac88525a593481ed93531", "generation_seconds_batch": 19.619587383931503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.54267954826355, "target_z": 4.343750018485626, "ce": 5.998785495758057, "genuineness": 4.400654315948486, "identity": 0.8129251003265381, "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_Contentment/41333e1cf245f844de2c1f24fdb45f1e9d184d196ef65111a47b1c48fa1f0a02.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "4166d6edba0fe7d5dbb455310889d5830ea7887b8caae3a5e82d00e2d05dc502", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "9ba410b6905f5503676d405c6ef552c05f11ee11c872ae4b25397928a5e2f8dd", "generation_seconds_batch": 17.379004957037978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7630958557128906, "target_z": 4.78124973010985, "ce": 6.340320587158203, "genuineness": 4.331617832183838, "identity": 0.3998672366142273, "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_Contentment/4166d6edba0fe7d5dbb455310889d5830ea7887b8caae3a5e82d00e2d05dc502.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "41f9db1036843e911a4c34c78272ed44c0078a74498467847aa3a0f894c4a041", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f91c3618c4bf36405f0cc874ea4d02abda98d05f6dbc4b07bbac850d8129e4ac", "generation_seconds_batch": 19.80973779410124, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4954473972320557, "target_z": 4.249999911268992, "ce": 6.292664527893066, "genuineness": 4.287685871124268, "identity": 0.34727776050567627, "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_Contentment/41f9db1036843e911a4c34c78272ed44c0078a74498467847aa3a0f894c4a041.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "42623a8782037db35531b8aa64e2c9b21162b4d94842c273f6a1db7f6deaec39", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "142697873743383c4b4742febd04b7ebba04d785124025c9393b257b499a9836", "generation_seconds_batch": 14.879864010028541, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7316079139709473, "target_z": 4.718749974120122, "ce": 6.133810997009277, "genuineness": 3.9550557136535645, "identity": 0.6773325800895691, "hypothesis": "Ha encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/42623a8782037db35531b8aa64e2c9b21162b4d94842c273f6a1db7f6deaec39.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "42cc8ea232105dab882e89e420b111fc2da28bece1741cf240950485767c47f8", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ab638a095f2ea88facf700395321c0f9d734fc3f2ed8ab0a45a639ca4cbb4ad8", "generation_seconds_batch": 20.32179498008918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3301351070404053, "target_z": 3.921875009242813, "ce": 5.990842819213867, "genuineness": 3.9425034523010254, "identity": 0.6047021746635437, "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_Contentment/42cc8ea232105dab882e89e420b111fc2da28bece1741cf240950485767c47f8.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": "43217fd458ce1ea6838db84531b135aaf2052a078dc318b90090942d08b1f996", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "4b89eb31cc926cdca366069b31b059dca1d523695ebd1e2e4ecf53da990a85a9", "generation_seconds_batch": 14.936294966028072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.141206741333008, "target_z": 3.5468750536083173, "ce": 6.006728172302246, "genuineness": 4.281409740447998, "identity": 0.6606196761131287, "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_Contentment/43217fd458ce1ea6838db84531b135aaf2052a078dc318b90090942d08b1f996.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "f25a76806fa2046527b3cf52f4aa88b449eaf637696403016b1d438182a3b5ed", "generation_seconds_batch": 14.363232800038531, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7948379516601562, "target_z": 2.8593748983290532, "ce": 6.157639026641846, "genuineness": 4.400654315948486, "identity": 0.6574711799621582, "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_Contentment/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "43cb88fbfcd3032b389ad7a1b48884515346a5e704cfad738795120ce039c94c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d235f1bbce333b8411427878f50383dc66a5e8027099de4c8e9fb0c6ef2589be", "generation_seconds_batch": 19.78082472400274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.141206741333008, "target_z": 3.5468750536083173, "ce": 6.316492557525635, "genuineness": 4.557555198669434, "identity": 0.5571178793907166, "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_Contentment/43cb88fbfcd3032b389ad7a1b48884515346a5e704cfad738795120ce039c94c.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": "43cc6f8b816b1a88771d539bf35b5f24f8e354a0bb4e6d68e617e8d51e5ff6d0", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1fc919d30743e923ecbffcdf6634c1387bfe43c4834666dfd5397d7a5e5fd5a7", "generation_seconds_batch": 19.390290445066057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1097185611724854, "target_z": 3.4843748243865464, "ce": 6.141753673553467, "genuineness": 4.15588903427124, "identity": 0.7290884852409363, "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_Contentment/43cc6f8b816b1a88771d539bf35b5f24f8e354a0bb4e6d68e617e8d51e5ff6d0.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": "43d535bd57149f9e846a76abae7846644959b6f2d3df26cffe72cacb5d4e497b", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2a511864e8bdd034a3cc3cfde0965eb60eec231ec9d0f084d301c13fbf7f9652", "generation_seconds_batch": 14.652536600013264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3380072116851807, "target_z": 3.937500184856267, "ce": 6.086154937744141, "genuineness": 4.281409740447998, "identity": 0.532233476638794, "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_Contentment/43d535bd57149f9e846a76abae7846644959b6f2d3df26cffe72cacb5d4e497b.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "2267a3611eed145b873d9b1cffdf71fa3163fa73340676f29f394f6586a71720", "generation_seconds_batch": 14.243307407945395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8656861782073975, "target_z": 3.0000000591540052, "ce": 6.197352409362793, "genuineness": 4.595211505889893, "identity": 0.689491868019104, "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_Contentment/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.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": "43fc0b55fd1acbc03932ccf577f4ef6862715d65bbcc2a119c91b98c3a432b81", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4ed2dac255492308c11806ad643e75cad9cc6114bd9889b47a096832bd869ed", "generation_seconds_batch": 14.43368711497169, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.054614543914795, "target_z": 3.3750000147885015, "ce": 6.268836498260498, "genuineness": 4.419482707977295, "identity": 0.45635637640953064, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunche 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_Contentment/43fc0b55fd1acbc03932ccf577f4ef6862715d65bbcc2a119c91b98c3a432b81.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": "444030fddb5e61d0de3e0523cad6d0c717d6d2bf65622610ba781d45b94cb880", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Escribí el número en el sobre.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f50827f0359b3e2d79bdfece28acb8591d29db44afc5d40c3903ea148540ae18", "generation_seconds_batch": 15.359538275981322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3852391242980957, "target_z": 4.031249818840858, "ce": 6.141753673553467, "genuineness": 4.425758361816406, "identity": 0.7138406038284302, "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_Contentment/444030fddb5e61d0de3e0523cad6d0c717d6d2bf65622610ba781d45b94cb880.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "4444749f4d402842c51f5e915c7aa11e5abe24e1e9de5e73d6ce5ba30f5af308", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "52d68bf67610a3ef497fc46df5fdf2453e8a80e42ae8c69dbc4051578052e985", "generation_seconds_batch": 19.577421439928003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.212054967880249, "target_z": 3.68750021443327, "ce": 6.284721851348877, "genuineness": 3.9425034523010254, "identity": 0.3646671772003174, "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_Contentment/4444749f4d402842c51f5e915c7aa11e5abe24e1e9de5e73d6ce5ba30f5af308.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "44490a6ab27091ca0ade16a406901efc94faa7f9480b44ba1eeb820afeedf051", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "9d844430a9b2bd0edc29437988732408111999f6230c91afc60f6ed0dc13ad2c", "generation_seconds_batch": 19.063470363034867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1805667877197266, "target_z": 3.6249999852114985, "ce": 6.125868320465088, "genuineness": 4.149612903594971, "identity": 0.6756564378738403, "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_Contentment/44490a6ab27091ca0ade16a406901efc94faa7f9480b44ba1eeb820afeedf051.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "447a4347a8d92b4eed2efdd717af73ec073ad1b028d63bd22b723ed4e00ed746", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d79dbe28f512c8b15898a98e7831697f5c148adfd0ca556a9130a5dc95465d9a", "generation_seconds_batch": 21.409804883995093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.212054967880249, "target_z": 3.68750021443327, "ce": 6.229123115539551, "genuineness": 4.20609712600708, "identity": 0.5151033401489258, "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_Contentment/447a4347a8d92b4eed2efdd717af73ec073ad1b028d63bd22b723ed4e00ed746.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "447b75eddb583e3520f02bf22c283dc8df9edcf62b1293741b905ef51cfbf7b9", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "df7d3257b8a69191b46545a3300d6c99386ea59065bb8b53c7412dae5178acf5", "generation_seconds_batch": 23.161672211950645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5111913681030273, "target_z": 4.281249789263856, "ce": 6.173524379730225, "genuineness": 4.425758361816406, "identity": 0.6484160423278809, "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_Contentment/447b75eddb583e3520f02bf22c283dc8df9edcf62b1293741b905ef51cfbf7b9.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "44d2a14297f51e9be1cd2958ba6204f58cf08e348f2afb2fc897ca7332f645b3", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "0d314b5b0807005c439c9ebf9705d9c910fdf15aba2eb13c25593dc60a0d692b", "generation_seconds_batch": 19.4048111140728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.275031089782715, "target_z": 3.8125001996447683, "ce": 6.292664527893066, "genuineness": 3.9927117824554443, "identity": 0.32868513464927673, "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_Contentment/44d2a14297f51e9be1cd2958ba6204f58cf08e348f2afb2fc897ca7332f645b3.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "44f9b3733063a64832d9bb7f7dbd8fa095e76d5f206eba192f631a54299c8c7d", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a92a72fb89604c634fa71411b2d1ba2be007918acfe414bff2bc36c0d0f7ab8d", "generation_seconds_batch": 20.63832199794706, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6452696323394775, "target_z": 2.5624998742977385, "ce": 6.268836498260498, "genuineness": 4.432034492492676, "identity": 0.5182778835296631, "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_Contentment/44f9b3733063a64832d9bb7f7dbd8fa095e76d5f206eba192f631a54299c8c7d.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "458f406850981721d6e34142d63555143ae8cf4f1c3fa233d4d0eb4ec8cd20e9", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4662ab12b113fab70e91d1614f5b947af54fd4c31874fecbd4d7091710a661f9", "generation_seconds_batch": 22.301203459035605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6925017833709717, "target_z": 2.656249981514373, "ce": 6.205295085906982, "genuineness": 4.262581825256348, "identity": 0.7134124040603638, "hypothesis": "De bur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/458f406850981721d6e34142d63555143ae8cf4f1c3fa233d4d0eb4ec8cd20e9.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": "45a458b472bed53c557a91c2bd2f9fe1ab9876109304bfa297bd41dfdbe2512e", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Someone moved the little blue chair.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "88b5a58ebc5294ad8749c448659c375d743290714bc31bcb8767b039d97ec7a3", "generation_seconds_batch": 14.603631907957606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6056556701660156, "target_z": 4.468750003697125, "ce": 6.475345611572266, "genuineness": 4.080576419830322, "identity": 0.20853957533836365, "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_Contentment/45a458b472bed53c557a91c2bd2f9fe1ab9876109304bfa297bd41dfdbe2512e.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "fbaf7bdeea3ad59337a3b73dffbb23389cfdb881634944cc0e1c98ad413f786a", "generation_seconds_batch": 15.256155075971037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7239898443222046, "target_z": 2.7187499741201226, "ce": 6.419747352600098, "genuineness": 4.093128204345703, "identity": 0.4344068765640259, "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_Contentment/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "4610de35b528893278db75c71180d0500145ac9ebb316afab27b58d430a500cd", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6506e852d7f4e7fe8524aa839281f20b1adc7f9f1394777fa5b834c94ed7f63d", "generation_seconds_batch": 20.06162208004389, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.43247127532959, "target_z": 4.124999926057493, "ce": 6.213237762451172, "genuineness": 4.362998008728027, "identity": 0.2501785159111023, "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_Contentment/4610de35b528893278db75c71180d0500145ac9ebb316afab27b58d430a500cd.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "4662bc8d132188f04f3874da08b09d9073f0b457f0e64d4c107e0b84d15f1883", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "16abbb2c849b4611f2c38842b8c77d20cea28854f1f24c51b5252eaa809407d2", "generation_seconds_batch": 19.930401496007107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4639594554901123, "target_z": 4.187500155279264, "ce": 5.959072113037109, "genuineness": 4.519899368286133, "identity": 0.6934918165206909, "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_Contentment/4662bc8d132188f04f3874da08b09d9073f0b457f0e64d4c107e0b84d15f1883.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "468fe2a6f68c1f56ef7d57f586e68ce624dae7ff7af5501851bfe744b96edd0a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "be8763dfc7075be31f406811f05bdd93c412ca602fccac54667533a497821fc2", "generation_seconds_batch": 19.289671808946878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0861027240753174, "target_z": 3.4375002440102724, "ce": 6.3641486167907715, "genuineness": 4.137060642242432, "identity": 0.7088809013366699, "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_Contentment/468fe2a6f68c1f56ef7d57f586e68ce624dae7ff7af5501851bfe744b96edd0a.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "4698e37f8d1c9a26a2b0cc0e93243632bf89df5187dddde4426fbe838407e09f", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "84eb962c1df30f80aa7cb7b96c396a74ef2fd6300e3d36e855191f5994b535b8", "generation_seconds_batch": 16.224442829960026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6059095859527588, "target_z": 2.4843749426945574, "ce": 6.173524379730225, "genuineness": 4.494794845581055, "identity": 0.4579774737358093, "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_Contentment/4698e37f8d1c9a26a2b0cc0e93243632bf89df5187dddde4426fbe838407e09f.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "478ad916253fd38fe01d5e3eb53a046f08f6ae492148c9a442a46b63d8d98902", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "65fd84a416e4c7ff75c7366d13ce2e75d4bef8b4ab99497056952698dcbec1b6", "generation_seconds_batch": 20.465708237024955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.164822816848755, "target_z": 3.5937501072166347, "ce": 6.395919322967529, "genuineness": 4.21237325668335, "identity": 0.5860493779182434, "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_Contentment/478ad916253fd38fe01d5e3eb53a046f08f6ae492148c9a442a46b63d8d98902.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "478fb66c8da17e8454d556acd8d661358a46aa557d81828e372e6862a3e1787d", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "60888c9c9e17193f8ee0304921f01c853d59d55b67ba453823302472c48fcdc1", "generation_seconds_batch": 19.27682355605066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.164822816848755, "target_z": 3.5937501072166347, "ce": 6.475345611572266, "genuineness": 4.218649387359619, "identity": 0.5143622756004333, "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_Contentment/478fb66c8da17e8454d556acd8d661358a46aa557d81828e372e6862a3e1787d.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": "479350aed848388be4faf36be17a8350a3990c5965340671b7f3bb0d8df99e90", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9d7de9cf69411f52a345616fd560b772ed5e00181747536ff77f81041c0f9f70", "generation_seconds_batch": 14.652536600013264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.164822816848755, "target_z": 3.5937501072166347, "ce": 6.149696350097656, "genuineness": 4.243753433227539, "identity": 0.6564500331878662, "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_Contentment/479350aed848388be4faf36be17a8350a3990c5965340671b7f3bb0d8df99e90.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "479a6880acebc90fb6f6947c814f26ff219806edf3fbc3f50c29c38b9aab00f7", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "fdc5f4a18fc2cf9757f2a87e8643483178d1d0fe507bc903f15009fcb1016a78", "generation_seconds_batch": 16.36724029807374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3380072116851807, "target_z": 3.937500184856267, "ce": 6.197352409362793, "genuineness": 4.162164688110352, "identity": 0.1787387877702713, "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_Contentment/479a6880acebc90fb6f6947c814f26ff219806edf3fbc3f50c29c38b9aab00f7.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "47ae73826bd8db584d42cb3b5ce00aebcf7b676a0a034e42bdec5a0d23bbf07b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b28b3d2976ecb4c12621d37bb0d0ebefa3c2e68f03d9de7605d8f20ae015bfb0", "generation_seconds_batch": 19.50856319896411, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8814301490783691, "target_z": 3.031249937148869, "ce": 6.292664527893066, "genuineness": 4.218649387359619, "identity": 0.6397751569747925, "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_Contentment/47ae73826bd8db584d42cb3b5ce00aebcf7b676a0a034e42bdec5a0d23bbf07b.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "54803d3c6ea5446fb2b896b0220be3621ece7ad9e3669ef712bfb5e08d1d6575", "generation_seconds_batch": 14.917436274001375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5822935104370117, "target_z": 2.4374998890862396, "ce": 6.157639026641846, "genuineness": 4.381826400756836, "identity": 0.706309974193573, "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_Contentment/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "4804071d7d9d3ad333acaeefd30693f13c1b0c99d6cd992b0b021fc6f94e228c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b8c648de063e093edac4f296f253272804bcfa1b69ca00f24a667add8e00df20", "generation_seconds_batch": 21.9554118210217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.101846694946289, "target_z": 3.468750122005136, "ce": 6.372091293334961, "genuineness": 4.300237655639648, "identity": 0.39368560910224915, "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_Contentment/4804071d7d9d3ad333acaeefd30693f13c1b0c99d6cd992b0b021fc6f94e228c.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": "492bdb9a4c1a21b58dcb7698373c1a813428aca5876cf0f202a07de08523d28d", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I wrote the number on the envelope.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "3188962a0c8a61b320ea6ba6f7e5c6815d505b7a16f8e89636a29c5ea8c9f7f5", "generation_seconds_batch": 14.54715107800439, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3616230487823486, "target_z": 3.9843747652325407, "ce": 6.356205940246582, "genuineness": 3.8044304847717285, "identity": 0.20868267118930817, "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_Contentment/492bdb9a4c1a21b58dcb7698373c1a813428aca5876cf0f202a07de08523d28d.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "49b33466526f75bf35cfb1856b76a02710e953fb6ee242350682429da7332f2a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "bf693436e4e5df45698a438eec0d57f3421133db83c32a205cb0c26dfdee0787", "generation_seconds_batch": 19.5981345360633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1729487180709839, "target_z": 1.6249999852114987, "ce": 6.348263263702393, "genuineness": 4.532451152801514, "identity": 0.6474218368530273, "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_Contentment/49b33466526f75bf35cfb1856b76a02710e953fb6ee242350682429da7332f2a.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "4f8f9ae9f350fd8896caffaf555b131da76655f21165fc181e3b002eafcf309c", "generation_seconds_batch": 14.445116898976266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.125462770462036, "target_z": 3.5156251756134536, "ce": 6.173524379730225, "genuineness": 4.20609712600708, "identity": 0.6257266998291016, "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_Contentment/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "4a1800c2329185635cc33960f4431ca78d3b6b81f5380c2972e376d5fcc47834", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "eabbeb91af77ff40d393e755314b6968505aef484d7dd7a80457353a16bd3337", "generation_seconds_batch": 14.647038997034542, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6213996410369873, "target_z": 4.4999998816919895, "ce": 6.403861999511719, "genuineness": 4.519899368286133, "identity": 0.4368000030517578, "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_Contentment/4a1800c2329185635cc33960f4431ca78d3b6b81f5380c2972e376d5fcc47834.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": "4a516a72cfd01cd4791c5771bd599ed8516f8b15abb01dcfa9d860759a72c3aa", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Someone moved the little blue chair.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4de64e653b81d2d146e43b2fac1a00bf62fae3ba306b03ea3ad285bd89a2223c", "generation_seconds_batch": 14.739135493990034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.700119733810425, "target_z": 4.656249744898352, "ce": 6.4912309646606445, "genuineness": 4.293961524963379, "identity": 0.26593953371047974, "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_Contentment/4a516a72cfd01cd4791c5771bd599ed8516f8b15abb01dcfa9d860759a72c3aa.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "4a613505a4c0fbf00cfac183c6dc71d739b62aa90bb058790790bbedb6d908a5", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f9a7a19bb9586c9bdd79eef908094038f5b54fe6cf9b0428ba97dbbbabbd7b38", "generation_seconds_batch": 16.69594410492573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.306519031524658, "target_z": 3.874999955634496, "ce": 6.395919322967529, "genuineness": 4.243753433227539, "identity": 0.5949692726135254, "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_Contentment/4a613505a4c0fbf00cfac183c6dc71d739b62aa90bb058790790bbedb6d908a5.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "4b1aceb0eb3cdaca59cf7e40bb33584ac65393e2b1962bf781b1e1df70560754", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "c4be4478b08d7b694a99f61c860681a196075407f489540cea14134c810b6489", "generation_seconds_batch": 19.696284055011347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.164822816848755, "target_z": 3.5937501072166347, "ce": 6.1894097328186035, "genuineness": 3.785602569580078, "identity": 0.30505311489105225, "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_Contentment/4b1aceb0eb3cdaca59cf7e40bb33584ac65393e2b1962bf781b1e1df70560754.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": "4b541f337764f81be862a5381c0ec59c897817fba90a2f5516594ff38bf023fe", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "56940f91bd033431866b8d3a5d29434924ac94e2bca1fd156b123834b9c2e6a1", "generation_seconds_batch": 19.623654350056313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1963107585906982, "target_z": 3.6562498632063622, "ce": 6.173524379730225, "genuineness": 4.149612903594971, "identity": 0.5672873854637146, "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_Contentment/4b541f337764f81be862a5381c0ec59c897817fba90a2f5516594ff38bf023fe.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "4b83214dfb54ed1c5620399b7b9f7f00936a5957b91399dc3e03c0516c019a76", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "cc5783863c4397dd9cfc6a42189a5fa03a4e7c0b61f02f5f1674c7f6f0f78caa", "generation_seconds_batch": 19.506171619985253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.345879077911377, "target_z": 3.953124887237677, "ce": 6.221180438995361, "genuineness": 4.432034492492676, "identity": 0.49836403131484985, "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_Contentment/4b83214dfb54ed1c5620399b7b9f7f00936a5957b91399dc3e03c0516c019a76.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": "4c25a6e6b74711ce445807746440253ffc24f32eb28b024e85d04ee1fc8c599d", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The road turns left behind the bridge.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "be3d81a8e2abd0a72e5697270af6c4caa08a62a65bff9694f6512c3570b1dcf0", "generation_seconds_batch": 14.374462175997905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2199268341064453, "target_z": 3.70312491681468, "ce": 6.459460258483887, "genuineness": 4.168440818786621, "identity": 0.13716953992843628, "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_Contentment/4c25a6e6b74711ce445807746440253ffc24f32eb28b024e85d04ee1fc8c599d.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "4c2b1588c164702d22dded849cfba825e61140760b7e697b7849dc4c060ffdbb", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b768b0dec41cd802dcd75d9f03119ee205608bf20c3e80955770b5a664866dd0", "generation_seconds_batch": 15.221701854025014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.062232494354248, "target_z": 5.374999778172479, "ce": 6.252951145172119, "genuineness": 4.13078498840332, "identity": 0.6545416116714478, "hypothesis": "En que he encontrado 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_Contentment/4c2b1588c164702d22dded849cfba825e61140760b7e697b7849dc4c060ffdbb.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "4c9018bb6d11e3fd14e847f1138d8ed5a2b47af763747e090c4e9bc1eeba4cfe", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "7b559ab0bba6e95a81f823231b066f128f7d3d17d1541ab7addd2cda218ea85e", "generation_seconds_batch": 19.590780700091273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.164822816848755, "target_z": 3.5937501072166347, "ce": 6.268836498260498, "genuineness": 4.319066047668457, "identity": 0.5860289335250854, "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_Contentment/4c9018bb6d11e3fd14e847f1138d8ed5a2b47af763747e090c4e9bc1eeba4cfe.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "4ccc4624082196f99f68a4f97d62fe35fd1a1766c0e89ddea1ef60c41db38998", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ebcc505e4b40b5f3a77a4b262613a2f8558fe759b1b39e37d2fdb196773c4ba4", "generation_seconds_batch": 19.4155606480781, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.164822816848755, "target_z": 3.5937501072166347, "ce": 5.7684478759765625, "genuineness": 3.785602569580078, "identity": 0.6576212644577026, "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_Contentment/4ccc4624082196f99f68a4f97d62fe35fd1a1766c0e89ddea1ef60c41db38998.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": "4d09b8426440ec576c8a85f5f1a4bd80e920dc4d8720064fb770fe149e9f47fb", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ceaef07ddbfb780bbb86efdcc98ab7f33d9791051fd621a1827148283530982a", "generation_seconds_batch": 15.2186626449693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2199268341064453, "target_z": 3.70312491681468, "ce": 6.260893821716309, "genuineness": 4.262581825256348, "identity": 0.5071799159049988, "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_Contentment/4d09b8426440ec576c8a85f5f1a4bd80e920dc4d8720064fb770fe149e9f47fb.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "4d23c6d1de422f3f79e5f8c5a3b2c74248a695c8367c45bad39c5906fab35368", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b16c4c7b6dd9cafcb98a5d7449394016256bc29747e0cb0c7f538b28e008fea4", "generation_seconds_batch": 14.914524774067104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.007382392883301, "target_z": 3.2812499075718664, "ce": 6.3641486167907715, "genuineness": 4.15588903427124, "identity": 0.5770343542098999, "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_Contentment/4d23c6d1de422f3f79e5f8c5a3b2c74248a695c8367c45bad39c5906fab35368.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "4d3d9e6a64a6f29677e20af114e191ee7f1ddf818bdd6d69928d15f2fe25eb03", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cd358093008068618ce9ab8119f662699b47d8b35875e479bda16357968df9ab", "generation_seconds_batch": 14.461725878994912, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.149078845977783, "target_z": 3.562500229221771, "ce": 6.284721851348877, "genuineness": 4.017816066741943, "identity": 0.575981855392456, "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_Contentment/4d3d9e6a64a6f29677e20af114e191ee7f1ddf818bdd6d69928d15f2fe25eb03.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": "4e176cbdbb5debe7e9cb6c16aeafb522cdace7fcc9e1a4cdf185d700e85ee645", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Your message arrived after I had left.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "64dc2ec120042a98ea3912a7c3610e390186f1badeb77b975c541ff55579aa21", "generation_seconds_batch": 19.15924824902322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2199268341064453, "target_z": 3.70312491681468, "ce": 6.467403411865234, "genuineness": 4.162164688110352, "identity": 0.31731659173965454, "hypothesis": "Your message arrived after I had left. I read it twice, before putting the phone away. Let me know and we can talk.", "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_Contentment/4e176cbdbb5debe7e9cb6c16aeafb522cdace7fcc9e1a4cdf185d700e85ee645.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "4f106a229c2bf2e11e2f4668a37c2574cf06a4a3ca198debe19830f79914fc59", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fe45ac9aeb183a1803b5ae8d0b86f434c6385e3ee270d3a2b0d030f5188ba1aa", "generation_seconds_batch": 14.160302937030792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8738120794296265, "target_z": 1.0312499371488693, "ce": 6.070269584655762, "genuineness": 4.300237655639648, "identity": 0.5845867395401001, "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_Contentment/4f106a229c2bf2e11e2f4668a37c2574cf06a4a3ca198debe19830f79914fc59.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": "4fc3c06648a1f1dccb56daa7475789ed171450e220db839fe9d275f11a594a92", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a74c70fc73ed9b83846899b8bd9fece8532ccdc9f05a1f6003735307670ab2f6", "generation_seconds_batch": 14.601529691019095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9837663173675537, "target_z": 3.234374853963549, "ce": 6.197352409362793, "genuineness": 4.607763767242432, "identity": 0.5642943382263184, "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_Contentment/4fc3c06648a1f1dccb56daa7475789ed171450e220db839fe9d275f11a594a92.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "4ffe5cd8208a24135c9637f4dfc4c973dff14f56394cfa43c14e48662a639b11", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "4262de9b631a2d77d64a7620b92b647d5f81dde91f11c9d2e6d03c007ba721da", "generation_seconds_batch": 19.808388652978465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.212054967880249, "target_z": 3.68750021443327, "ce": 6.403861999511719, "genuineness": 3.7793264389038086, "identity": 0.5007051825523376, "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_Contentment/4ffe5cd8208a24135c9637f4dfc4c973dff14f56394cfa43c14e48662a639b11.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "5063adb5efb4efa83b27b06fdbfd86f48f6c618484c6c5216c1e4a3ef9cb0fca", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "640d4d359e92b5092d727c6564ca541c21f5d1fcfb5ca144f753f100fc0d655b", "generation_seconds_batch": 19.5981345360633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8777481317520142, "target_z": 1.039062524955596, "ce": 6.070269584655762, "genuineness": 4.344170093536377, "identity": 0.6673085689544678, "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_Contentment/5063adb5efb4efa83b27b06fdbfd86f48f6c618484c6c5216c1e4a3ef9cb0fca.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "5070581cca896422d74748b00bc5a11df2f7555cba2501cc9f411842544c3414", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "392c1d89214520fc8137534a50098acdedf297b932a0e4d82526432a98f34089", "generation_seconds_batch": 19.14165550796315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4482152462005615, "target_z": 4.156249804052357, "ce": 6.117925643920898, "genuineness": 4.457139015197754, "identity": 0.5052261352539062, "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_Contentment/5070581cca896422d74748b00bc5a11df2f7555cba2501cc9f411842544c3414.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": "50d4c9cdf5d3f59ddf14f6b3666903b974a41fd3d2a1a3f758eb601bef2dc19f", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b847f4df40bf2d050e9f4a48d6ebd6c2f6dd405c272769f867969d1cfffc6184", "generation_seconds_batch": 15.18735123402439, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4954473972320557, "target_z": 4.249999911268992, "ce": 6.316492557525635, "genuineness": 4.419482707977295, "identity": 0.715088963508606, "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_Contentment/50d4c9cdf5d3f59ddf14f6b3666903b974a41fd3d2a1a3f758eb601bef2dc19f.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "50e24818bcb2c2b4bfdde1aa7c8ce97c993e521626de0c6a23a677e3973f85e2", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f48b31c9f1f88a59be4f2383eb52a20b21dd5788931edd9ed867c2c3a2b0ce3c", "generation_seconds_batch": 14.400635089026764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.637143611907959, "target_z": 4.531249759686853, "ce": 6.467403411865234, "genuineness": 4.381826400756836, "identity": 0.3523004949092865, "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_Contentment/50e24818bcb2c2b4bfdde1aa7c8ce97c993e521626de0c6a23a677e3973f85e2.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "523e3e19364bf3dc5b670715f2d97be950f43dd9370074ccca02de56559bdfb6", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e23c2a6bb63d41ea6c8f4eea435f058acc673893cd69d0ecb1692479a11ecade", "generation_seconds_batch": 16.582272604922764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2514150142669678, "target_z": 3.765625146036451, "ce": 6.0305562019348145, "genuineness": 4.482243061065674, "identity": 0.7316724061965942, "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_Contentment/523e3e19364bf3dc5b670715f2d97be950f43dd9370074ccca02de56559bdfb6.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": "5264190603b0f23eebf3ee75ed16f48a7cfa893847b71d9017b16dd89f53a2ed", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d664aca648b96eab54948ca233a42b136208a679beb7c2f9c8dbc6e8e0c6ecc7", "generation_seconds_batch": 19.534607921959832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.188438892364502, "target_z": 3.6406251608249525, "ce": 6.38003396987915, "genuineness": 4.218649387359619, "identity": 0.5638203620910645, "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_Contentment/5264190603b0f23eebf3ee75ed16f48a7cfa893847b71d9017b16dd89f53a2ed.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "52967402b06b0ad67e1b57019328c11a515c041817077f415785fbf09170bc4b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b140ecdcd68f80e48a2b13f0f337e3517af61eea1240152fd8ba2ef234aafedb", "generation_seconds_batch": 21.399024946033023, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.542933464050293, "target_z": 2.3593749574830585, "ce": 6.23706579208374, "genuineness": 4.494794845581055, "identity": 0.47151055932044983, "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_Contentment/52967402b06b0ad67e1b57019328c11a515c041817077f415785fbf09170bc4b.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "5296ecd4f67cb29c11c458567fe6e6a874b437a86285293f1b5284d6dd569410", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "4415b7316c2dd99249129301f2112b77e49aacca6f6f8150dabf14da44d8663c", "generation_seconds_batch": 19.296316997963004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2671589851379395, "target_z": 3.7968750240313147, "ce": 6.3641486167907715, "genuineness": 4.143336772918701, "identity": 0.594415009021759, "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_Contentment/5296ecd4f67cb29c11c458567fe6e6a874b437a86285293f1b5284d6dd569410.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": "535a47b9607f5368c2cddc23dcda5c2e7b0f46be7b60dc86facbffe61e70e064", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f1162354cfd050b42127b25cd00d00f19e645529fd9c915bf5ec33a43c43f387", "generation_seconds_batch": 15.100125383003615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7788400650024414, "target_z": 4.812500081336758, "ce": 6.284721851348877, "genuineness": 4.137060642242432, "identity": 0.6875445246696472, "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_Contentment/535a47b9607f5368c2cddc23dcda5c2e7b0f46be7b60dc86facbffe61e70e064.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "5365a9ca1bf6dfcd37ecf18d6bf917170c7a93c2fd567bda1b9f7bc1f68781dd", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "09393c4253414c99995939c7dfc692dc7f4e4ea6ae858aaafce76e8f2d8353b2", "generation_seconds_batch": 19.578423509025015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9837663173675537, "target_z": 3.234374853963549, "ce": 6.284721851348877, "genuineness": 4.256305694580078, "identity": 0.43309107422828674, "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_Contentment/5365a9ca1bf6dfcd37ecf18d6bf917170c7a93c2fd567bda1b9f7bc1f68781dd.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "53a1d2890f60a0120cdf2042ebf44c1a9eaee8ccf30c9d3538460d2bd2af5ed1", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c2aeadfa139eb9a24bd7d6a4249ee69b08cb1ae9bcf714f7ad4af091e6a64555", "generation_seconds_batch": 14.098628266947344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4954473972320557, "target_z": 4.249999911268992, "ce": 6.2767791748046875, "genuineness": 4.444586753845215, "identity": 0.809989333152771, "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_Contentment/53a1d2890f60a0120cdf2042ebf44c1a9eaee8ccf30c9d3538460d2bd2af5ed1.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "53c01c433e6b702256457f104e2a59488c3cada3ce321e25b078f8d30e530397", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "200a7a8d4308930380264c2e24e5acbd55bb4a18ed675dbc11195776007180cf", "generation_seconds_batch": 21.643775925040245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0861027240753174, "target_z": 3.4375002440102724, "ce": 6.24500846862793, "genuineness": 4.507347106933594, "identity": 0.7141080498695374, "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_Contentment/53c01c433e6b702256457f104e2a59488c3cada3ce321e25b078f8d30e530397.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "53c8bb08d4f7f2570b2e8700bceb65590b6e6c8791c835a94f8ad4d2a14042de", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b7cec3184be767c0ac56885bab55d1303676f9070b2526051c2b777b6c48372c", "generation_seconds_batch": 22.514221188030206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4009833335876465, "target_z": 4.062500170067765, "ce": 6.125868320465088, "genuineness": 4.162164688110352, "identity": 0.6274065971374512, "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_Contentment/53c8bb08d4f7f2570b2e8700bceb65590b6e6c8791c835a94f8ad4d2a14042de.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "53efb0da616c8b2e2be1b04059b17573003f5fd1e85fc78101f0176557638a72", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "978baf630ea50b7804a5f84e1a404d290ff610ee01b28f0549232d9829516c29", "generation_seconds_batch": 19.57745108800009, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.43247127532959, "target_z": 4.124999926057493, "ce": 6.09409761428833, "genuineness": 4.218649387359619, "identity": 0.49168336391448975, "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_Contentment/53efb0da616c8b2e2be1b04059b17573003f5fd1e85fc78101f0176557638a72.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "5433e6dbd842ab57390d8311e2c7a7b87aa96c6eec4aedcbf9d4bf50765d0b05", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "3fdf0e583e9547cec2e9e65142352e2133d29313ecc01e49efb5b08fd3457446", "generation_seconds_batch": 19.106445117969997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6528878211975098, "target_z": 4.56250011091376, "ce": 6.125868320465088, "genuineness": 4.325342178344727, "identity": 0.4712704122066498, "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_Contentment/5433e6dbd842ab57390d8311e2c7a7b87aa96c6eec4aedcbf9d4bf50765d0b05.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "a438afde028580f6ed9c06306dc64f042d39ca0d5c3e8b47d2840b21b05bfa17", "generation_seconds_batch": 15.256155075971037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8971742391586304, "target_z": 3.0625000517597547, "ce": 6.356205940246582, "genuineness": 4.005263805389404, "identity": 0.3291921615600586, "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_Contentment/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "54a7c5d108526925aa948aac779c864033ab6ed56a316286d0b8e48b848cb196", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ceb051cc7d8bcbd32c1be28a19ba6b1e982094a2ec52e2146d850cfc0f8b0402", "generation_seconds_batch": 19.657666228013113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.54267954826355, "target_z": 4.343750018485626, "ce": 6.443574905395508, "genuineness": 4.319066047668457, "identity": 0.2818518579006195, "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_Contentment/54a7c5d108526925aa948aac779c864033ab6ed56a316286d0b8e48b848cb196.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "5569b5b9f7cd6fab562c296bfa269e88b5efe7183f78947f90bbfe4b8553df68", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "648d30f6721a4df9c009cfd108cc2e0effbc13b28f7cfc5bce2baa20b7dfef55", "generation_seconds_batch": 19.602233020938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.149078845977783, "target_z": 3.562500229221771, "ce": 5.974957466125488, "genuineness": 3.8546390533447266, "identity": 0.4580557644367218, "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_Contentment/5569b5b9f7cd6fab562c296bfa269e88b5efe7183f78947f90bbfe4b8553df68.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "558e8f20c9012b9eed69317f739f9e6826c48c9c0263248a645e29027746d55f", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ac675cec62b1a93eb14c2e7fb4c19c3b0ee5a87bc6392860a47a6e28da2bfed0", "generation_seconds_batch": 14.914524774067104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3380072116851807, "target_z": 3.937500184856267, "ce": 6.475345611572266, "genuineness": 4.105680465698242, "identity": 0.5045146942138672, "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_Contentment/558e8f20c9012b9eed69317f739f9e6826c48c9c0263248a645e29027746d55f.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "5617c470abe5730c92eb485980e55f08ca71fc24480d577d443f05ba0f7376d6", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "150ea34f38aedb5e06ba18e125e074246e7f47dc81d7502ef6268607b5d258c1", "generation_seconds_batch": 19.248446488985792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1726949214935303, "target_z": 3.6093752828300887, "ce": 6.181467056274414, "genuineness": 4.381826400756836, "identity": 0.5720674991607666, "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_Contentment/5617c470abe5730c92eb485980e55f08ca71fc24480d577d443f05ba0f7376d6.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "564219eb0b44516baee293023c777a6624c5fd1c0fef4d20bc0e445b4fca20d1", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "fe4807b897f6d3fb872a03b97f1856216f6b19dd73a70ae6c96ba4126d9cd0b3", "generation_seconds_batch": 23.994906384963542, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.149078845977783, "target_z": 3.562500229221771, "ce": 6.252951145172119, "genuineness": 4.118232727050781, "identity": 0.7601320743560791, "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_Contentment/564219eb0b44516baee293023c777a6624c5fd1c0fef4d20bc0e445b4fca20d1.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "56768faf0d7f4ed4305a140774a048775f505d974847d89ab6ff03b7c46de513", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "c93101c483e609c5edc2b2a077446fec458298f79405c75a71b80c1bd6a1dc33", "generation_seconds_batch": 21.903045715996996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.007382392883301, "target_z": 3.2812499075718664, "ce": 6.1020402908325195, "genuineness": 4.3127899169921875, "identity": 0.6110800504684448, "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_Contentment/56768faf0d7f4ed4305a140774a048775f505d974847d89ab6ff03b7c46de513.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "56a243576ef8862bc7e02b5b40f5bb70dbad249b3d118095b1f5af97163abfb0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "71bb4578154ac30e7c91bbf43d65a9bf43c1b7c9e638dc906e985ac88271269f", "generation_seconds_batch": 19.106445117969997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7158639430999756, "target_z": 4.687500096125259, "ce": 6.205295085906982, "genuineness": 4.287685871124268, "identity": 0.7272833585739136, "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_Contentment/56a243576ef8862bc7e02b5b40f5bb70dbad249b3d118095b1f5af97163abfb0.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "56b9648223babf7086f34a62061e159ba0b95fd6c1428cf6b1f73904edc65267", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2af9324c75ebbe02feb0f36cbe411732bfe28de54a27c2151405595475c31641", "generation_seconds_batch": 22.576964769978076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.141206741333008, "target_z": 3.5468750536083173, "ce": 6.078212261199951, "genuineness": 4.356721878051758, "identity": 0.6659406423568726, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen daar samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/56b9648223babf7086f34a62061e159ba0b95fd6c1428cf6b1f73904edc65267.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "57881c63f4b8b074307f23d5ca1632ecea8a4a7bd9227eb74d0ead9464c74978", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "aa1df9ec5ca78dbe9ba9617e0b629a6be8ff4df25fc084d4b07df56e1877afae", "generation_seconds_batch": 22.148466433980502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4954473972320557, "target_z": 4.249999911268992, "ce": 6.0305562019348145, "genuineness": 4.042920112609863, "identity": 0.49199190735816956, "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_Contentment/57881c63f4b8b074307f23d5ca1632ecea8a4a7bd9227eb74d0ead9464c74978.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": "57a14b7721ce4110e102c08139ace5e79c1dc44641630c42f5d3d31388a8d9fb", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "164686920d0968c7324cf090f4a599fc9b76e235bed53bb179cfc8c408ff140d", "generation_seconds_batch": 19.534607921959832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.32226300239563, "target_z": 3.9062498336293596, "ce": 6.308549880981445, "genuineness": 4.15588903427124, "identity": 0.5815489292144775, "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_Contentment/57a14b7721ce4110e102c08139ace5e79c1dc44641630c42f5d3d31388a8d9fb.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "582c0f98598820004d817e8691a3bbf4fe7c38f2e899ed44ff5bdd8963758a9c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "69fb2008ac76df27e6a62f3a59c1dbdea0a27769de40358b4d606a1cdbe082ba", "generation_seconds_batch": 19.53361879696604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.259286880493164, "target_z": 3.781249848417861, "ce": 6.38797664642334, "genuineness": 4.093128204345703, "identity": 0.5620142817497253, "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_Contentment/582c0f98598820004d817e8691a3bbf4fe7c38f2e899ed44ff5bdd8963758a9c.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "586bb524f3e376ba191dbe9bc46aca7aa7e457a012f6daba1dde9960977b955c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "9070a182829242433845deaf1ec36232aca59209d09736e7c0fa9ce4dd09a8a5", "generation_seconds_batch": 19.58510578190908, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.164822816848755, "target_z": 3.5937501072166347, "ce": 6.292664527893066, "genuineness": 4.406930446624756, "identity": 0.7908604145050049, "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_Contentment/586bb524f3e376ba191dbe9bc46aca7aa7e457a012f6daba1dde9960977b955c.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "589744b12ab73594e1335d505340c27fa39a2d504808cac984d9976e4789b7df", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "58cffc49f76179a2076ca4822f93dc4be057644c2aabe7b0aea3cf5e01546f19", "generation_seconds_batch": 19.343779332004488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0861027240753174, "target_z": 3.4375002440102724, "ce": 6.292664527893066, "genuineness": 4.381826400756836, "identity": 0.5273233652114868, "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_Contentment/589744b12ab73594e1335d505340c27fa39a2d504808cac984d9976e4789b7df.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "58d2408638168eeead2712c61e25e596d3a4f741c69ee83604d3f069cce0e66c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ae474c4bbf86b73d417a36da4b12403bbadd7a459a3791d7efed778a81e3b2b4", "generation_seconds_batch": 20.454924631980248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.54267954826355, "target_z": 4.343750018485626, "ce": 6.3641486167907715, "genuineness": 4.7458367347717285, "identity": 0.7526568174362183, "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_Contentment/58d2408638168eeead2712c61e25e596d3a4f741c69ee83604d3f069cce0e66c.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "59437b599f464a23f9984898ca6110ba1bf04e382179a52a1c2d6512f1c5a4fc", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "685c55c9059ce660dfabdd92d018a07a858e7de92fcbea9b8c14875b55e8e8d5", "generation_seconds_batch": 14.903395778033882, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.282902956008911, "target_z": 3.8281249020261785, "ce": 6.340320587158203, "genuineness": 4.2374773025512695, "identity": 0.32944971323013306, "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_Contentment/59437b599f464a23f9984898ca6110ba1bf04e382179a52a1c2d6512f1c5a4fc.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "59d3ae8b60fd8cdb87b351f4c33a28cf97ea20038fdb2416a9b3d2479af2dd43", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d4369f89a62a1d06701ff16cb542a82fd57482ad0449f1573cbc0a593d3c54db", "generation_seconds_batch": 19.982844781014137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.282902956008911, "target_z": 3.8281249020261785, "ce": 6.157639026641846, "genuineness": 4.331617832183838, "identity": 0.684640645980835, "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_Contentment/59d3ae8b60fd8cdb87b351f4c33a28cf97ea20038fdb2416a9b3d2479af2dd43.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "5a6154264ff90f09ef95d69687c71c93624c4a09455f6307ba5a90bf6eadb63d", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d64f1a99d86b1fb51a9e6b879d9ba0198f67b38471c5a6dd34b2d63e290c631e", "generation_seconds_batch": 19.56050372205209, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4954473972320557, "target_z": 4.249999911268992, "ce": 6.316492557525635, "genuineness": 4.356721878051758, "identity": 0.4411166310310364, "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_Contentment/5a6154264ff90f09ef95d69687c71c93624c4a09455f6307ba5a90bf6eadb63d.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "5a8ca4186e4d97265137e51463da1061beca6c5189759f92ae5ae25ab762e2ae", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "5abee4367b9419ce14e634e734bb31418892f4f18c092115ebc492b3d248b755", "generation_seconds_batch": 21.12270346004516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9522782564163208, "target_z": 3.1718748613577996, "ce": 6.205295085906982, "genuineness": 3.936227321624756, "identity": 0.6509202122688293, "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_Contentment/5a8ca4186e4d97265137e51463da1061beca6c5189759f92ae5ae25ab762e2ae.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "5ab44f9969688fdcc5a1efb1735d1ebac3ad31660088e98bcaf0b2cf69a1fc42", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d6b6fc45707f85688962ffe582236fd2b49c9040434f0a8163bedbefb3c1f716", "generation_seconds_batch": 20.046449268003926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5111913681030273, "target_z": 4.281249789263856, "ce": 6.38797664642334, "genuineness": 4.149612903594971, "identity": 0.06499013304710388, "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_Contentment/5ab44f9969688fdcc5a1efb1735d1ebac3ad31660088e98bcaf0b2cf69a1fc42.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "5ad33f19f0819e9d31a191319e181ceb6f8187ba02b6bee6e55c51256ded77c5", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "db597f093c1c1e619beff69da4b9ba05da0d760187a2178b382115ac0d2e4d8f", "generation_seconds_batch": 19.94228988199029, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.684375762939453, "target_z": 4.6249998669034875, "ce": 6.109982967376709, "genuineness": 4.406930446624756, "identity": 0.6297112107276917, "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_Contentment/5ad33f19f0819e9d31a191319e181ceb6f8187ba02b6bee6e55c51256ded77c5.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "5b2055af4995034143878b073b95a5d31fe4a19c92b844bb1a7133aa0336a0db", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "b61df5943e7eea7dfa5dec3e07dafcb6d2e3332e011e771e52ec7445db663e04", "generation_seconds_batch": 19.386066977051087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.700119733810425, "target_z": 4.656249744898352, "ce": 6.165581703186035, "genuineness": 4.281409740447998, "identity": 0.6010486483573914, "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_Contentment/5b2055af4995034143878b073b95a5d31fe4a19c92b844bb1a7133aa0336a0db.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": "5bb716b84dce293e37aa32e47483fd00780aa4c178921d0e933c60cf0b35dbcd", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Your message arrived after I had left.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e2fd887ab66d72287f5d50b30afbdaf2d1e29277759362b7ab776fdbde5bcdf1", "generation_seconds_batch": 14.261590243084356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.149078845977783, "target_z": 3.562500229221771, "ce": 6.38003396987915, "genuineness": 4.362998008728027, "identity": 0.2528367340564728, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/5bb716b84dce293e37aa32e47483fd00780aa4c178921d0e933c60cf0b35dbcd.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "5bdf5f4a4c96eebabd500320a63fad483b94f61929d5b2e7c0d1c60df8816d79", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "178127820dc90f9d86243a95a78516967c81ee213a0c50a513d360fa32cb7185", "generation_seconds_batch": 19.687784363981336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2199268341064453, "target_z": 3.70312491681468, "ce": 6.213237762451172, "genuineness": 4.287685871124268, "identity": 0.7980412244796753, "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_Contentment/5bdf5f4a4c96eebabd500320a63fad483b94f61929d5b2e7c0d1c60df8816d79.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": "5c68ab41ba094ed99dff4cbad0acfc7c8958f708275a5105ac25fe1596ab78aa", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "aff16c35f0e6229654a3c65a756d15941a54136fb82c572a93468cd207977a0d", "generation_seconds_batch": 14.651468673022464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3852391242980957, "target_z": 4.031249818840858, "ce": 6.292664527893066, "genuineness": 4.080576419830322, "identity": 0.36782634258270264, "hypothesis": "Die Schlösser 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_Contentment/5c68ab41ba094ed99dff4cbad0acfc7c8958f708275a5105ac25fe1596ab78aa.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": "5c98626784252ca80c4e223c4fd4330806588db723d2e5d65b8eaa1f79e41d87", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "c78bd5548d79d5061056844cb164c7f7739f0113e067e6777a3b67148015870c", "generation_seconds_batch": 14.49359802203253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.282902956008911, "target_z": 3.8281249020261785, "ce": 6.213237762451172, "genuineness": 4.3881025314331055, "identity": 0.7602003812789917, "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_Contentment/5c98626784252ca80c4e223c4fd4330806588db723d2e5d65b8eaa1f79e41d87.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "5d0db18fcc2bd6d509b80da9ffdd6b62fd32a486c962021f717dd93c38a17c3a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "aa6acc7d1efabbf498bac2759c77b5a5783f46f18151b823a3980e472111bf68", "generation_seconds_batch": 14.488189007970504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4954473972320557, "target_z": 4.249999911268992, "ce": 6.340320587158203, "genuineness": 4.482243061065674, "identity": 0.7516222596168518, "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_Contentment/5d0db18fcc2bd6d509b80da9ffdd6b62fd32a486c962021f717dd93c38a17c3a.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "5d68ddee8a98d563d63ce4c9ccb7712cf3b9b136406e3f6985a2613e5b6c8182", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "c9ab9d4bbb46e38206f1c15a1bf2a8f62e39ac38c25c890c2e0158371c1a4997", "generation_seconds_batch": 19.14165550796315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6686317920684814, "target_z": 4.593749988908624, "ce": 6.2767791748046875, "genuineness": 4.168440818786621, "identity": 0.5108559131622314, "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_Contentment/5d68ddee8a98d563d63ce4c9ccb7712cf3b9b136406e3f6985a2613e5b6c8182.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "5d8374313ee99df0c18075d7825c9d1e996d4085f60d922d6f09411d27de1c98", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b40b1e0aac0401893f9ecbae6ece3963b44980c2dcba5af26060219f230ac5aa", "generation_seconds_batch": 19.9463481339626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4954473972320557, "target_z": 4.249999911268992, "ce": 6.292664527893066, "genuineness": 4.6956281661987305, "identity": 0.7445526123046875, "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_Contentment/5d8374313ee99df0c18075d7825c9d1e996d4085f60d922d6f09411d27de1c98.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "5dd88ce5c2c82214c67f8b518243d13059d969361cd55cb5deac36d55d8e0649", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2b83d7591167d50042861786a65012053f26c7a83a2874c2c4583f2bcb42e925", "generation_seconds_batch": 19.55137224297505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.149078845977783, "target_z": 3.562500229221771, "ce": 6.3641486167907715, "genuineness": 4.118232727050781, "identity": 0.65004563331604, "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_Contentment/5dd88ce5c2c82214c67f8b518243d13059d969361cd55cb5deac36d55d8e0649.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "9d17f9bc21b9e6168369845fe4d538abd3d4165a0d8d54bddb339751f4dff346", "generation_seconds_batch": 14.783017495064996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.834197998046875, "target_z": 2.9374998299322344, "ce": 6.070269584655762, "genuineness": 4.331617832183838, "identity": 0.7845841646194458, "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_Contentment/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "5edfa859380cf80eda942b18f6b7e45d35159bc416cb12b7dbbdd5858d479323", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "357d112a640ce993a30a61d078618534e5f8198319b86309a1f558591c82532c", "generation_seconds_batch": 16.610794609994628, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2514150142669678, "target_z": 3.765625146036451, "ce": 6.300607204437256, "genuineness": 4.469690799713135, "identity": 0.521894633769989, "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_Contentment/5edfa859380cf80eda942b18f6b7e45d35159bc416cb12b7dbbdd5858d479323.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "5fbf1b8149abb293adbf5822ad31855945f5382f73676176c9c83326b561b329", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "299fbc3808b8031ad163e6fe6003885e62997fec23f77699f08f072c96284af8", "generation_seconds_batch": 20.42362422903534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.416727304458618, "target_z": 4.093750048062629, "ce": 6.23706579208374, "genuineness": 4.645420074462891, "identity": 0.7519651651382446, "hypothesis": "J'ai trouvé la petite boîte. Elle était elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/5fbf1b8149abb293adbf5822ad31855945f5382f73676176c9c83326b561b329.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "608086e9333f5efc5282c6db06b7eefcaa3aba85c46864a2c384c544128dfd3b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d1257f17dd61c2ee5c956dbbe0c518c689bf576cccb68b2917711407ec3789ce", "generation_seconds_batch": 19.452995316009037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6213996410369873, "target_z": 4.4999998816919895, "ce": 6.221180438995361, "genuineness": 4.1998209953308105, "identity": 0.518513023853302, "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_Contentment/608086e9333f5efc5282c6db06b7eefcaa3aba85c46864a2c384c544128dfd3b.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "6166ff5521ca545d3deb79fee9e5ce5482ee1e904d9759593b88f9ccbdeaad76", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f71efa4a9d73601db2bd1505fc65552f57f77fa172df530ae06f78a0bcc8dcf2", "generation_seconds_batch": 14.346214115968905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.526935577392578, "target_z": 4.312500140490763, "ce": 6.125868320465088, "genuineness": 4.18099308013916, "identity": 0.3277406096458435, "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_Contentment/6166ff5521ca545d3deb79fee9e5ce5482ee1e904d9759593b88f9ccbdeaad76.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "61698efddcc6ccdc2180de519c3de729138004cc21f15a7d6b2ca82ba20a2995", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "02087d5581305f85d01210da488d3c3a5571658fe4e3149815c9218fd62d634a", "generation_seconds_batch": 19.342325179022737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.212054967880249, "target_z": 3.68750021443327, "ce": 6.507116317749023, "genuineness": 4.193545341491699, "identity": 0.6169537305831909, "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_Contentment/61698efddcc6ccdc2180de519c3de729138004cc21f15a7d6b2ca82ba20a2995.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "61f04e2b7eb66f40ac34bdb0c99b14be908849a093b3345dbb33f4c1db1f560d", "bucket": "emo_Contentment", "phase": "wording", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "aa0ca0ed3927660e6ee346f257f826756d5f36d836baedd85096767c732e12dd", "generation_seconds_batch": 15.651001809048466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.54267954826355, "target_z": 4.343750018485626, "ce": 6.459460258483887, "genuineness": 4.394378662109375, "identity": 0.20406369864940643, "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_Contentment/61f04e2b7eb66f40ac34bdb0c99b14be908849a093b3345dbb33f4c1db1f560d.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "620c10343eeed298373f318e5a18cd83708e57ca365c73d37ceeda112e48f41b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "eb7130540a52dad3c25d040258d79c0ba76b0633eef103e7512fcdbfeaebbd68", "generation_seconds_batch": 20.17940120899584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.637143611907959, "target_z": 4.531249759686853, "ce": 6.221180438995361, "genuineness": 4.381826400756836, "identity": 0.6672029495239258, "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_Contentment/620c10343eeed298373f318e5a18cd83708e57ca365c73d37ceeda112e48f41b.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "624ea427adc6a989f1a655d91a772294609d105cf2d2b003cc93eedbf743d304", "bucket": "emo_Contentment", "phase": "wording", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e741d9b41cbd4277f99917561c73b917ad7ff5c75c1dbd044a58e237f44e6701", "generation_seconds_batch": 15.689225109061226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9286623001098633, "target_z": 3.125000044365504, "ce": 5.95112943649292, "genuineness": 3.860914945602417, "identity": 0.6775537133216858, "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_Contentment/624ea427adc6a989f1a655d91a772294609d105cf2d2b003cc93eedbf743d304.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "62f00b538a2f316fb5cf0011ec00a1a53b5978322796be9d8fb6cb900ec5455d", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "6c67ba3635bd21725a8fb3a5036a4c0ea99d0cee50de4c97d5adcf153f497277", "generation_seconds_batch": 16.849004243966192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4954473972320557, "target_z": 4.249999911268992, "ce": 6.213237762451172, "genuineness": 4.444586753845215, "identity": 0.5450398921966553, "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_Contentment/62f00b538a2f316fb5cf0011ec00a1a53b5978322796be9d8fb6cb900ec5455d.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "6388cb3f9edfc645ea51819bdf5d807bfcd2b413ce973ac2f978978a7800f6b3", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "7d0c156637a90a4a66bab3124635737cd9d493f272e34687990a8b94d60b00a6", "generation_seconds_batch": 20.500792959937826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0939745903015137, "target_z": 3.4531249463916827, "ce": 6.09409761428833, "genuineness": 4.369274139404297, "identity": 0.5638599991798401, "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_Contentment/6388cb3f9edfc645ea51819bdf5d807bfcd2b413ce973ac2f978978a7800f6b3.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "63c92f470e81cd829b73cf14b4c2ac20dac3fb6ffbcdc96ae532ea4147d3ea2c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "c1f981f5ce5bc216d269436d3cd8f6e172605aea3fac070110a4b1bd5216315c", "generation_seconds_batch": 19.83019646606408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.542933464050293, "target_z": 2.3593749574830585, "ce": 6.133810997009277, "genuineness": 4.293961524963379, "identity": 0.675630509853363, "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_Contentment/63c92f470e81cd829b73cf14b4c2ac20dac3fb6ffbcdc96ae532ea4147d3ea2c.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "63eb368116a09a8fa16b986cd0a5821cba7a674447118f96e891514b54f148da", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d845d72c70807ac26266e9ad2760f0dfb5711c8c96cec933e50b638f606c4730", "generation_seconds_batch": 20.896110223955475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.369495153427124, "target_z": 3.9999999408459948, "ce": 5.9431867599487305, "genuineness": 3.9801597595214844, "identity": 0.551151692867279, "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_Contentment/63eb368116a09a8fa16b986cd0a5821cba7a674447118f96e891514b54f148da.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "63ee6ea673d4e7bfccd7b979fa76b0c77793cda0828f97b90bcd446425578cb3", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "c1d338e90d468b6c36084143b1ccdbed948f574b9b717db5708eb994b7fb3fb9", "generation_seconds_batch": 23.453917777049355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7869659662246704, "target_z": 2.843749959331621, "ce": 5.982900142669678, "genuineness": 4.017816066741943, "identity": 0.46718090772628784, "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_Contentment/63ee6ea673d4e7bfccd7b979fa76b0c77793cda0828f97b90bcd446425578cb3.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "641200b8bed2c17e350ca28ce4689991289f9076bfecf1e98af700b38a5678d8", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2b045c2596ef27cb909581aa4b5cd7c26f66c51fc2ca853ab322e6732ff4d142", "generation_seconds_batch": 21.562577673001215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5584235191345215, "target_z": 4.374999896480491, "ce": 6.443574905395508, "genuineness": 4.595211505889893, "identity": 0.5492273569107056, "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_Contentment/641200b8bed2c17e350ca28ce4689991289f9076bfecf1e98af700b38a5678d8.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "6416cb93ad6755a7d625609da4a578237eb8f1e4887c3df5f84d217dcfd1c7c0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "aa12e54afd09e5e3d1aeba496df87256e82c108e5b92cf20cbfd93e2ffbd8ab7", "generation_seconds_batch": 20.452680178917944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.416727304458618, "target_z": 4.093750048062629, "ce": 6.252951145172119, "genuineness": 4.344170093536377, "identity": 0.6430297493934631, "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_Contentment/6416cb93ad6755a7d625609da4a578237eb8f1e4887c3df5f84d217dcfd1c7c0.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "64fc836b4e6c83b07501c78c837e3458061ca51d6ac1d49640ab476fbf6a5fae", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b98338c6d7d9a48595612838685c3130b3c24266c32a455f5972046ab7b1e216", "generation_seconds_batch": 20.433204947039485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.416727304458618, "target_z": 4.093750048062629, "ce": 6.292664527893066, "genuineness": 3.8671910762786865, "identity": 0.27285313606262207, "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_Contentment/64fc836b4e6c83b07501c78c837e3458061ca51d6ac1d49640ab476fbf6a5fae.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "651a49423ff2a0a77d07ec6ab0e4539b4d45eab081fc4af9b7dde4ecd59f0275", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "50eaccd32590e8237da48f50233de79e442574b657b03d794804285aa3949a33", "generation_seconds_batch": 20.75561525905505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.589911699295044, "target_z": 4.437500125702262, "ce": 6.308549880981445, "genuineness": 4.369274139404297, "identity": 0.5701055526733398, "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_Contentment/651a49423ff2a0a77d07ec6ab0e4539b4d45eab081fc4af9b7dde4ecd59f0275.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "6586fe2fede119ea8c99a1855c7715d8393e76f9edcdf20ca0e7f97375326899", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "529da6fdd6522e09afdc3f521e5b51be1b90a686c60e0d1c9eefe198b230ede8", "generation_seconds_batch": 20.148076451965608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7316079139709473, "target_z": 4.718749974120122, "ce": 6.046441555023193, "genuineness": 4.086852550506592, "identity": 0.5032757520675659, "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_Contentment/6586fe2fede119ea8c99a1855c7715d8393e76f9edcdf20ca0e7f97375326899.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "65c1ebf3ddf1a312c2aa3db78de7341085f73b88e2240d31bf9fab2b044c2384", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "c6fd38d58b2cf2c5073db18b48f9e3193e0b8b1824ef1ac11c5e10944999135a", "generation_seconds_batch": 19.136294177966192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4009833335876465, "target_z": 4.062500170067765, "ce": 6.300607204437256, "genuineness": 3.9927117824554443, "identity": 0.3986402750015259, "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_Contentment/65c1ebf3ddf1a312c2aa3db78de7341085f73b88e2240d31bf9fab2b044c2384.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "65ff0f6f7cf97f1ba8950cfb7caa8f56ce834501cf6a7c8fe575f389eecd3133", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "fd813d7d91fcf17bef9609f99a7ee28a63fd7bc2638c0ce8cdac55501a9de8d5", "generation_seconds_batch": 16.076387881068513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4954473972320557, "target_z": 4.249999911268992, "ce": 6.006728172302246, "genuineness": 4.632867813110352, "identity": 0.783207893371582, "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_Contentment/65ff0f6f7cf97f1ba8950cfb7caa8f56ce834501cf6a7c8fe575f389eecd3133.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "6655c618993019d76631eb82568d89253ca38b80d6e161b7021ae2fc59441cae", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "43ada84c67d52ed2e5b5965030e9753074f6e932c6012ba7b296b67a53a21abb", "generation_seconds_batch": 19.4656971039949, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.889302134513855, "target_z": 3.046874876146301, "ce": 6.125868320465088, "genuineness": 4.300237655639648, "identity": 0.6968505382537842, "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_Contentment/6655c618993019d76631eb82568d89253ca38b80d6e161b7021ae2fc59441cae.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "66615159be577ac48de4dd5fbf76785353e37a19cbd0112bcafd0818be72a30e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "4066db284d7b32475b2cf498e4489719c1b9e1f65b16669eb66c80f15de14b94", "generation_seconds_batch": 21.260849826969206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.306519031524658, "target_z": 3.874999955634496, "ce": 6.316492557525635, "genuineness": 4.005263805389404, "identity": 0.15080903470516205, "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_Contentment/66615159be577ac48de4dd5fbf76785353e37a19cbd0112bcafd0818be72a30e.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "667fa65762f526bec0744bc030b35f4586e3b0ad8641a6d9fae81bf33b075aef", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "aba8dfc620d42da6f67ce1cab9201d3a59f81cff836fa02b97458962d2b8e413", "generation_seconds_batch": 23.0220710770227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1805667877197266, "target_z": 3.6249999852114985, "ce": 6.260893821716309, "genuineness": 4.381826400756836, "identity": 0.6266700029373169, "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_Contentment/667fa65762f526bec0744bc030b35f4586e3b0ad8641a6d9fae81bf33b075aef.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "6688157f64b848fb726417dfc51baee2c0f5612f86340b5955c6035c83791299", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "3fc43bf33dbb642b19138549f3a393a99bd9866f43c722ddc0d4b0594981e56e", "generation_seconds_batch": 17.385060355998576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9205362796783447, "target_z": 5.093749929754619, "ce": 6.268836498260498, "genuineness": 4.061748504638672, "identity": 0.5286391973495483, "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_Contentment/6688157f64b848fb726417dfc51baee2c0f5612f86340b5955c6035c83791299.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "673c43e30d67521efeae8ca099c35c0d9ec1be4b4a0b69707f0c1badb84c27d8", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f6e8cee1738a9a8799e9711cbcab0f213b7b4a34d1a12498982cc3d2a85085ac", "generation_seconds_batch": 23.0220710770227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.054614543914795, "target_z": 3.3750000147885015, "ce": 6.356205940246582, "genuineness": 4.250029563903809, "identity": 0.6828102469444275, "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_Contentment/673c43e30d67521efeae8ca099c35c0d9ec1be4b4a0b69707f0c1badb84c27d8.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "6774d2083b9aad1f199936ca6568b127bfff0c171255af2f64422fa0f4c4f4af", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "3bd1a2073408fda09d859cbce93bc095646d8516469d1cf3d00588e5413ea842", "generation_seconds_batch": 20.29879096103832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7630958557128906, "target_z": 4.78124973010985, "ce": 6.117925643920898, "genuineness": 3.9676074981689453, "identity": 0.6267880201339722, "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_Contentment/6774d2083b9aad1f199936ca6568b127bfff0c171255af2f64422fa0f4c4f4af.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "681cdcd2386a2d198bc8052f524fee9f9437d4ed6928a8df0d6ca5d0751161ba", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "398046f6ce707e2d8e9d2a660cf68e210c3eb30eb4495245d91edfaa86a5dcf2", "generation_seconds_batch": 20.406746561056934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5271893739700317, "target_z": 2.3281248428721733, "ce": 6.229123115539551, "genuineness": 4.494794845581055, "identity": 0.64289391040802, "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_Contentment/681cdcd2386a2d198bc8052f524fee9f9437d4ed6928a8df0d6ca5d0751161ba.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "689423c5aeb7bdd05211c6b1edf55d9e3561d9713f867ab9a1adcfaba5b93c1c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "8808834bb4f8831ac380a3958914b6f6d86aa5f00ac0d5d9fe35b9132a28443a", "generation_seconds_batch": 21.610677831922658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4639594554901123, "target_z": 4.187500155279264, "ce": 5.919358730316162, "genuineness": 4.118232727050781, "identity": 0.6069416999816895, "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_Contentment/689423c5aeb7bdd05211c6b1edf55d9e3561d9713f867ab9a1adcfaba5b93c1c.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "68e7a64b872f73764dc0a403e42bd7b8d1aefcc3c3bcaba9a8c9341039d61603", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b6e97cf4ade31788bcff44fb9bc9b30fea592fad187757a63e7684cf9cf0d1d9", "generation_seconds_batch": 20.7740468790289, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7869659662246704, "target_z": 2.843749959331621, "ce": 6.213237762451172, "genuineness": 4.18099308013916, "identity": 0.21101616322994232, "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_Contentment/68e7a64b872f73764dc0a403e42bd7b8d1aefcc3c3bcaba9a8c9341039d61603.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "69092a64c4a07a342a2fb30b6a9175cbca91eb7820a489462f25e36af559d7af", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "649928e95de2c9b03cec46b5094f475d96f8a57753791e3a235fd071979f5cad", "generation_seconds_batch": 20.540258308988996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2514150142669678, "target_z": 3.765625146036451, "ce": 6.205295085906982, "genuineness": 4.15588903427124, "identity": 0.15111318230628967, "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_Contentment/69092a64c4a07a342a2fb30b6a9175cbca91eb7820a489462f25e36af559d7af.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "694fe82c9ea615cf3422b13315fb305487074c2f35431b94c20cd9e1f8cd4dc1", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0097e61fa64682c1be100a85208e14271c9af9c8ad02303fcee2520635563d15", "generation_seconds_batch": 22.301203459035605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3933651447296143, "target_z": 2.0624999334517438, "ce": 6.157639026641846, "genuineness": 4.419482707977295, "identity": 0.44129201769828796, "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_Contentment/694fe82c9ea615cf3422b13315fb305487074c2f35431b94c20cd9e1f8cd4dc1.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "69610e04c1a938c95d2cec0e4212228519d6d80fbac13e3bb8249838f6b4c7a5", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b9c5fab99895d9417dc760124d789c64d890c7fd8a6c34f618876dd5ae59610b", "generation_seconds_batch": 14.427359698922373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2041828632354736, "target_z": 3.6718750388198163, "ce": 6.229123115539551, "genuineness": 3.8671910762786865, "identity": 0.3071281313896179, "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_Contentment/69610e04c1a938c95d2cec0e4212228519d6d80fbac13e3bb8249838f6b4c7a5.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "69b978815ce3ec921ea71a9f2922dc85559dbcb0a8f8b724e4811457102ed103", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "79f92f4a2ce28412e4e195570bdb73aaf47377da34be350ecac55b1fe3b8cd1c", "generation_seconds_batch": 22.974822315969504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3537511825561523, "target_z": 3.968750062851131, "ce": 6.316492557525635, "genuineness": 4.118232727050781, "identity": 0.1945597529411316, "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_Contentment/69b978815ce3ec921ea71a9f2922dc85559dbcb0a8f8b724e4811457102ed103.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "69c8ffb72604257c6ae93ed04a8d2ecb14a66588553de153fd8559c4f880860e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d2f05640acf19e54cb5815a031444984ab04560dc417ad5a468b58992f0d4de5", "generation_seconds_batch": 21.109212653012946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.43247127532959, "target_z": 4.124999926057493, "ce": 6.332377910614014, "genuineness": 4.337893962860107, "identity": 0.6730179786682129, "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_Contentment/69c8ffb72604257c6ae93ed04a8d2ecb14a66588553de153fd8559c4f880860e.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "69f199f49ab7d2d8f56849ed51dad7fc2c30f6ca4d5d5783f1acca64ea51a452", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e6f0ca64e4856d401cf074613c2bcf823545f46bc97fb634ac14641fbc1f83dd", "generation_seconds_batch": 14.877906944020651, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.991638422012329, "target_z": 3.2500000295770026, "ce": 6.332377910614014, "genuineness": 4.394378662109375, "identity": 0.47825995087623596, "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_Contentment/69f199f49ab7d2d8f56849ed51dad7fc2c30f6ca4d5d5783f1acca64ea51a452.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "6a1b8bf67fa54dd19aed4360878f408f623ecd63622743808742e7e7b65f4cb3", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "83d12891f6ed058604ab6f1d4990444e2a7e212c8bdf2e28f824237fe7e0b61b", "generation_seconds_batch": 14.44584268797189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0467424392700195, "target_z": 3.3593748391750475, "ce": 6.141753673553467, "genuineness": 4.457139015197754, "identity": 0.7654584050178528, "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_Contentment/6a1b8bf67fa54dd19aed4360878f408f623ecd63622743808742e7e7b65f4cb3.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1a2f8f8fdfff3c3326dcd625bf127af8ffcaf4740e8d22b2c48a2b44f427126f", "generation_seconds_batch": 14.88742979906965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.078230619430542, "target_z": 3.421875068396819, "ce": 6.395919322967529, "genuineness": 4.055472373962402, "identity": 0.1656504124403, "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_Contentment/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "6ade3fa18a51ce3ba66516e33aee4427b90374c00e480868086ea2427491dc55", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "02d6077e3dc72a583991f5902c5ac8f11a00da25771a32d734512a8cb1b6cc4c", "generation_seconds_batch": 19.53594679501839, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.275031089782715, "target_z": 3.8125001996447683, "ce": 6.221180438995361, "genuineness": 4.319066047668457, "identity": 0.5429666042327881, "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_Contentment/6ade3fa18a51ce3ba66516e33aee4427b90374c00e480868086ea2427491dc55.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "6adfa96c405a83d12b2180cf64bd2db6ecb1e4e497eaa8cd4aba5a9eafa78ee2", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "47308022feebd339811abdb24c96c50a4e9846674a5711a99280b76a0b114be2", "generation_seconds_batch": 16.69594410492573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2435429096221924, "target_z": 3.7499999704229974, "ce": 6.3641486167907715, "genuineness": 4.13078498840332, "identity": 0.6531764268875122, "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_Contentment/6adfa96c405a83d12b2180cf64bd2db6ecb1e4e497eaa8cd4aba5a9eafa78ee2.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": "6b6359cdf32ab8f083bf10c5ce27f76dc4435b016beb415277c81111e843c93b", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2c03b26a167dafe3ff42e3218778f12450c2d7df81b92e7d5eba9f654bb00e3b", "generation_seconds_batch": 14.522594542941079, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8420701026916504, "target_z": 2.953125005545688, "ce": 6.205295085906982, "genuineness": 4.406930446624756, "identity": 0.7539688348770142, "hypothesis": "Ik schreef het nummer op de envelop, lees het goed en controleer de laatste twee cijfers, wel me hen wanneer je even tijd hebt.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/6b6359cdf32ab8f083bf10c5ce27f76dc4435b016beb415277c81111e843c93b.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": "6b8e2e466313c82c3bf00c24cf9d059099f1d393e80d7e409c4e97522439cd5d", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f7efab5a0acaa72da3479c5ea1e175a7836177bd43b1ed06f1992e296fc41ca5", "generation_seconds_batch": 14.624484202009626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.054614543914795, "target_z": 3.3750000147885015, "ce": 6.41180419921875, "genuineness": 4.557555198669434, "identity": 0.6239916086196899, "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_Contentment/6b8e2e466313c82c3bf00c24cf9d059099f1d393e80d7e409c4e97522439cd5d.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "4d247855ba7d2a9af67c8320395763a31b3b25f3acba1e897276a0e599a9cb82", "generation_seconds_batch": 14.243307407945395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8184540271759033, "target_z": 2.9062499519373706, "ce": 6.165581703186035, "genuineness": 4.469690799713135, "identity": 0.6612852215766907, "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_Contentment/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "6b9d04f84ba58be47d90ef54c0f2677f16a0c6c10bb1d0adea5cfc0612637520", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "10ea24443df98ea54bbda698661cc3d00f914e875f178067d171c0083813de19", "generation_seconds_batch": 19.78508611698635, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4639594554901123, "target_z": 4.187500155279264, "ce": 6.340320587158203, "genuineness": 3.8546390533447266, "identity": 0.27494269609451294, "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_Contentment/6b9d04f84ba58be47d90ef54c0f2677f16a0c6c10bb1d0adea5cfc0612637520.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "6c0cf0ee0400c10ecbe633f14ee24f2c5c89268338b2d7c86d59887da1da9bd2", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "5149d16d2ce26407f68b469f2fd02261848d845a4eb48f2f80f408234075f861", "generation_seconds_batch": 15.832512318040244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.589911699295044, "target_z": 4.437500125702262, "ce": 6.435632705688477, "genuineness": 4.532451152801514, "identity": 0.3802597224712372, "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_Contentment/6c0cf0ee0400c10ecbe633f14ee24f2c5c89268338b2d7c86d59887da1da9bd2.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": "6c3deccbdef55e8fd599bbb5e3b245059131686f8cc7e517e151b2132cb76266", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b61273735b661324cf2e5b7c26494258a426edff2a2f97ae516d2d76a2af5b7f", "generation_seconds_batch": 19.39140638394747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.306519031524658, "target_z": 3.874999955634496, "ce": 6.483288764953613, "genuineness": 4.457139015197754, "identity": 0.6103153824806213, "hypothesis": "Eine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg, sag mir, wann wir reden können.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/6c3deccbdef55e8fd599bbb5e3b245059131686f8cc7e517e151b2132cb76266.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "6c52d1f39deab91989fa63cf92c41cc432c9355ac149b737251a88772f26bd15", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "06b150784ad6fd0005d80e3b2f7f56b14c3470a4dbec1dbd300aab6e6b661e28", "generation_seconds_batch": 22.881160077056848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6213996410369873, "target_z": 4.4999998816919895, "ce": 6.268836498260498, "genuineness": 4.68307638168335, "identity": 0.5473658442497253, "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_Contentment/6c52d1f39deab91989fa63cf92c41cc432c9355ac149b737251a88772f26bd15.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "6c7240ed31a8bf590722603633dfd05342bcb0e997f8856ec078f0573a7c82d8", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "07add19298d9edf50366db4d07fc325245b1195b29175f592e8c03acf33b5bd9", "generation_seconds_batch": 19.183279406046495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3380072116851807, "target_z": 3.937500184856267, "ce": 5.974957466125488, "genuineness": 3.7165660858154297, "identity": 0.5007950067520142, "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_Contentment/6c7240ed31a8bf590722603633dfd05342bcb0e997f8856ec078f0573a7c82d8.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "6c779aed8bdecda03ae0d5dfba2084920b556db505ab9ff3e54aaef37b36ca49", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a63a125ce69e8396a372fae15defd68e392b7c32cd1cc5e914761461a64b32c7", "generation_seconds_batch": 19.872224841965362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.235671043395996, "target_z": 3.734375268041587, "ce": 6.308549880981445, "genuineness": 4.099404335021973, "identity": 0.5738435387611389, "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_Contentment/6c779aed8bdecda03ae0d5dfba2084920b556db505ab9ff3e54aaef37b36ca49.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "6cd574bcb2e9aa30be5c3a2054d66e59651fb56ce7595c296db657cd5be5bb27", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d59a9535ad010aee21756aa23cca0c468eb9c6449a8d4f8d26629c71d6fd1342", "generation_seconds_batch": 14.258096136967652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7869659662246704, "target_z": 2.843749959331621, "ce": 6.205295085906982, "genuineness": 4.030367851257324, "identity": 0.7274071574211121, "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_Contentment/6cd574bcb2e9aa30be5c3a2054d66e59651fb56ce7595c296db657cd5be5bb27.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "6db88d14a85eecdacbe3c2121f22201041983af13700ce864f3c73675ab491d8", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "8c37bc14d3cad739a964ae5fa00748642ab3f07ce6cffc509b70aa3b9b1be2b6", "generation_seconds_batch": 21.889463757979684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.574167490005493, "target_z": 4.406249774475354, "ce": 6.475345611572266, "genuineness": 4.369274139404297, "identity": 0.3280666470527649, "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_Contentment/6db88d14a85eecdacbe3c2121f22201041983af13700ce864f3c73675ab491d8.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "6e46160b5a7a2787572aa34d417eeb44fbd8b821c627e13b10d606c2753eb63e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "20244f83171c052f6167d9eb4572b75db9d3c176a9191cfc6e6f31af2c654408", "generation_seconds_batch": 14.84521505003795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.369495153427124, "target_z": 3.9999999408459948, "ce": 6.268836498260498, "genuineness": 4.362998008728027, "identity": 0.5850438475608826, "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_Contentment/6e46160b5a7a2787572aa34d417eeb44fbd8b821c627e13b10d606c2753eb63e.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "6f1d1beda86399312bd8a206c04ebb5898072fb516a46145b865b7418129a880", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "83cc63719e4381c354d30ad91870b962e6821cacc4e3ac27e14c7beaa63e82e7", "generation_seconds_batch": 19.811674798023887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.857814073562622, "target_z": 2.9843748835405517, "ce": 6.260893821716309, "genuineness": 4.457139015197754, "identity": 0.7038137912750244, "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_Contentment/6f1d1beda86399312bd8a206c04ebb5898072fb516a46145b865b7418129a880.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "6f3c8c6dec80c5dbbed7989fa17b6d8e87c1417f6e2fa62e711067587d4ba30c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d282ed0ed970d677405f6b13396ac360b3bac47d1ca76fcbfb58f525a9d61c70", "generation_seconds_batch": 22.613303494057618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2907750606536865, "target_z": 3.843750077639632, "ce": 6.340320587158203, "genuineness": 4.406930446624756, "identity": 0.6737891435623169, "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_Contentment/6f3c8c6dec80c5dbbed7989fa17b6d8e87c1417f6e2fa62e711067587d4ba30c.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "6fac90b857ffb250a245de97e231b061f995183f783ea8406d7324e3c4bf45dd", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a1e719b4d5b58d99c65bffb68ad52df67bf28af08191394c6f29ae1c7236036c", "generation_seconds_batch": 20.29879096103832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5111913681030273, "target_z": 4.281249789263856, "ce": 5.998785495758057, "genuineness": 4.099404335021973, "identity": 0.47630774974823, "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_Contentment/6fac90b857ffb250a245de97e231b061f995183f783ea8406d7324e3c4bf45dd.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "70b33736f1a86801b63250233058386c264445e031225e0ad52a172ccfc73e14", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2057eb2e47f0649978c44de926fcf6a6406060dee0e065dfa8c16d14af7da84f", "generation_seconds_batch": 23.034723059972748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.479703426361084, "target_z": 4.218750033274128, "ce": 6.284721851348877, "genuineness": 4.319066047668457, "identity": 0.6479408740997314, "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_Contentment/70b33736f1a86801b63250233058386c264445e031225e0ad52a172ccfc73e14.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "714ff4bca6496f92e28944f8d901b85b08d4ddc49dc839ddcd2a34fa05fc0edc", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3c8147db3741f4a6396b5baacdd7fdede2284788de7ce3c5a7f0dcb6b00e00e6", "generation_seconds_batch": 14.098628266947344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.574167490005493, "target_z": 4.406249774475354, "ce": 6.165581703186035, "genuineness": 4.632867813110352, "identity": 0.8286159038543701, "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_Contentment/714ff4bca6496f92e28944f8d901b85b08d4ddc49dc839ddcd2a34fa05fc0edc.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": "718658c4406e12c3bc8c1b548b82614ecd4fc8a51bd36fcc567a3b352fab6cbf", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I wrote the number on the envelope.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9d2e10e1972313e9daac5c68ceaee9ceef66a2d3f4b9df3776b98cd3ed8eba09", "generation_seconds_batch": 19.44601815205533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1569507122039795, "target_z": 3.578124931603181, "ce": 6.38003396987915, "genuineness": 4.068024158477783, "identity": 0.16633030772209167, "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_Contentment/718658c4406e12c3bc8c1b548b82614ecd4fc8a51bd36fcc567a3b352fab6cbf.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "726e274060ad42874d696f27200d61d2e22d3315e330f2f95c3388c234380a84", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "b72a81c62a4c4a5c74a1d0bee411a27f62a90af61862b668f406042f6505430c", "generation_seconds_batch": 19.822374399984255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0703585147857666, "target_z": 3.4062498927833653, "ce": 6.197352409362793, "genuineness": 4.268857479095459, "identity": 0.6871848702430725, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/726e274060ad42874d696f27200d61d2e22d3315e330f2f95c3388c234380a84.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": "72b58e18a8eafe9c525cc875834a42fc4e8c5d09a2f30386cdb1ffe533aa2a3b", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d710e261cad093c325b397792978fa4d2505ddd3afad4d9301a173543fdfd5a8", "generation_seconds_batch": 21.79814751003869, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2435429096221924, "target_z": 3.7499999704229974, "ce": 6.1894097328186035, "genuineness": 4.105680465698242, "identity": 0.39360398054122925, "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_Contentment/72b58e18a8eafe9c525cc875834a42fc4e8c5d09a2f30386cdb1ffe533aa2a3b.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "72d238d4156afd57f20b3d03e7afec8d6adbb7d5923594f52951a2bf1f890980", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2b5d492131572a9b3bccec5e742f7bf5aec8cfe9c9ffae9af72787946a89523a", "generation_seconds_batch": 16.74979054101277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3380072116851807, "target_z": 3.937500184856267, "ce": 6.205295085906982, "genuineness": 4.425758361816406, "identity": 0.6557672023773193, "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_Contentment/72d238d4156afd57f20b3d03e7afec8d6adbb7d5923594f52951a2bf1f890980.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "731480827bb94f77e58e09f36acf4cac3f3cedbdb1c62fee33616aa8b32e575b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d85eb747e640770a7daa9c5e540a81e9a1bf019c76bc085e474cbc5c4976d59d", "generation_seconds_batch": 19.80973779410124, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5584235191345215, "target_z": 4.374999896480491, "ce": 6.3641486167907715, "genuineness": 4.20609712600708, "identity": 0.3087736964225769, "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_Contentment/731480827bb94f77e58e09f36acf4cac3f3cedbdb1c62fee33616aa8b32e575b.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "73406b1fbefebb15cf357a95cbe7efd22c40e793b565805ac0038f73c30a978e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9ae9639bc1e45d2262fcd3b93c89f7e05df47dcfd88ad8ed9921533dcb2da32d", "generation_seconds_batch": 20.91859691904392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.43247127532959, "target_z": 4.124999926057493, "ce": 6.117925643920898, "genuineness": 4.532451152801514, "identity": 0.8474826812744141, "hypothesis": "Je trouvai la petite boîte, elle était près d'eux la vieille fenêtre, nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.15789473684210525, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/73406b1fbefebb15cf357a95cbe7efd22c40e793b565805ac0038f73c30a978e.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "73eaa6c7d8659253935c816c9386042613358c9c4355425e9153dcdcb399b11d", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2942eb7167ef041e6569b897d8617edb1cc0550e2ef51684df87e6f9b42ca9a2", "generation_seconds_batch": 19.872224841965362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.306519031524658, "target_z": 3.874999955634496, "ce": 6.435632705688477, "genuineness": 4.394378662109375, "identity": 0.3282639980316162, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/73eaa6c7d8659253935c816c9386042613358c9c4355425e9153dcdcb399b11d.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "73eb9a8f34e2e3c0b11f347d4bc473154ebbdb86ac1b3c18a5d20ec8e822ba4b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "37f86ae8e9b4d27699be0bb974cd4130ca23c0a9f80d9379dac44b2cd887c8bc", "generation_seconds_batch": 16.262243852950633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.235671043395996, "target_z": 3.734375268041587, "ce": 6.260893821716309, "genuineness": 4.457139015197754, "identity": 0.620404839515686, "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_Contentment/73eb9a8f34e2e3c0b11f347d4bc473154ebbdb86ac1b3c18a5d20ec8e822ba4b.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "741e4a502af2f5b5126fa3bdce41617e0b72b8feaf6aa55d0355f9e55dfce875", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "607f75af5369f78032b269033f0d87174ecdb26f369bbe1d0c770e653e07ee18", "generation_seconds_batch": 19.414420333923772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2671589851379395, "target_z": 3.7968750240313147, "ce": 6.229123115539551, "genuineness": 4.193545341491699, "identity": 0.40396469831466675, "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_Contentment/741e4a502af2f5b5126fa3bdce41617e0b72b8feaf6aa55d0355f9e55dfce875.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": "746edb760f55901461a069a98e7b9ec7d2aeeba8ed26491dc0dbc7ca02141e72", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The road turns left behind the bridge.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "afad87ff7987cf978371cef10b5b0ce1aec1082c81d442de7a5a51e11ffea22d", "generation_seconds_batch": 14.682357870973647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2277989387512207, "target_z": 3.7187500924281336, "ce": 6.41180419921875, "genuineness": 3.961331605911255, "identity": 0.2784477472305298, "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_Contentment/746edb760f55901461a069a98e7b9ec7d2aeeba8ed26491dc0dbc7ca02141e72.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "74e1a5cf387f539442751705a8318a1a4d0e71d3164285b05e84916aaa1ff0f2", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c3a7746c6664118e5347adf21319ff20f42008a32c1d08fe166b17dd68089c5f", "generation_seconds_batch": 16.29015353298746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.298647165298462, "target_z": 3.8593752532530856, "ce": 6.157639026641846, "genuineness": 3.9173994064331055, "identity": 0.3510577380657196, "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_Contentment/74e1a5cf387f539442751705a8318a1a4d0e71d3164285b05e84916aaa1ff0f2.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "75186d7a35d2d3abc2c88c3866c2d140295be2236f2fb2aab1a4797a32cdb4ab", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "01bfdd29c4a153bad5c5c4ee4a1c476bc5089b6a4263954ac25357fb851a6a47", "generation_seconds_batch": 14.379008766030893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4954473972320557, "target_z": 4.249999911268992, "ce": 6.133810997009277, "genuineness": 4.582659721374512, "identity": 0.6644603610038757, "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_Contentment/75186d7a35d2d3abc2c88c3866c2d140295be2236f2fb2aab1a4797a32cdb4ab.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "751a9792e2eccbcb66a717a8f9eb89d61d1905d6cd0e25ca2f0a8d8082c59ae4", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2d97138ad0adafc982ccdf260ceaef8566004606471ed7db52775b166d34137b", "generation_seconds_batch": 14.708721422939561, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3537511825561523, "target_z": 3.968750062851131, "ce": 6.221180438995361, "genuineness": 4.074300289154053, "identity": 0.1870005577802658, "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_Contentment/751a9792e2eccbcb66a717a8f9eb89d61d1905d6cd0e25ca2f0a8d8082c59ae4.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": "754657d4a9908f07dc57dd618a040d384c55e60edf768287457141495a7f2b37", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "4d90f7febd0db1bc48df20640a55b54e9a37c34004e2f5079e1ec66d9d306d9c", "generation_seconds_batch": 14.54414551903028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0703585147857666, "target_z": 3.4062498927833653, "ce": 6.292664527893066, "genuineness": 3.9299514293670654, "identity": 0.283470094203949, "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_Contentment/754657d4a9908f07dc57dd618a040d384c55e60edf768287457141495a7f2b37.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "75b909322764b4639208631eadacdda205b372b00ec6f45f123c2ec6e9db2175", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "8b5d30da0de3c2b4af64b89a619ffec42e2f84a882bf1ab6a89d27cbb034b19d", "generation_seconds_batch": 15.342227032058872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1963107585906982, "target_z": 3.6562498632063622, "ce": 6.157639026641846, "genuineness": 4.394378662109375, "identity": 0.6524049043655396, "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_Contentment/75b909322764b4639208631eadacdda205b372b00ec6f45f123c2ec6e9db2175.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "75dd3215484565bc6606736021af13b09f566b98643e383f39781f58889e989f", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "49a92a4d1803feff40ab961de545770c657356e73b5fb7e90fd56b8fe353e14e", "generation_seconds_batch": 20.130340456031263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4484692811965942, "target_z": 2.1718749796658106, "ce": 6.09409761428833, "genuineness": 4.356721878051758, "identity": 0.6928547620773315, "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_Contentment/75dd3215484565bc6606736021af13b09f566b98643e383f39781f58889e989f.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "7619bb0c84caab70af8af5352975ea00e4cfc362684d0f2172cc7daa6d9a3cf7", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e91e11541698db2ddb736631cf6cb874199245a639436bc568e5caf2b9959bb0", "generation_seconds_batch": 19.474665535031818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.834197998046875, "target_z": 2.9374998299322344, "ce": 6.292664527893066, "genuineness": 4.319066047668457, "identity": 0.600114107131958, "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_Contentment/7619bb0c84caab70af8af5352975ea00e4cfc362684d0f2172cc7daa6d9a3cf7.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "7647921b003164a0988314582447b7717ec62bb001878f8fe761ef2b1c911787", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d451b1cba9a9b7f8e8f938c0c28bbab4395d344fdd287d8ba66c46281ef9448e", "generation_seconds_batch": 19.952623106073588, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5271893739700317, "target_z": 2.3281248428721733, "ce": 6.157639026641846, "genuineness": 4.268857479095459, "identity": 0.5137902498245239, "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_Contentment/7647921b003164a0988314582447b7717ec62bb001878f8fe761ef2b1c911787.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "4d66bb4e953c132a120662139a2a2ef652df25d1040e22f42396601029f353af", "generation_seconds_batch": 14.917436274001375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6610137224197388, "target_z": 2.593749988908624, "ce": 6.109982967376709, "genuineness": 4.494794845581055, "identity": 0.7308783531188965, "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_Contentment/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "77a95aaa5f6a4de854aaf4631d24a6fdc7e945aef185e3c6bcd43618757eafad", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "adf4eeb6b432b1b8497f8bc8fe26d72af51e564e9ccb0d138f8ffd544eee2dbd", "generation_seconds_batch": 14.379008766030893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.700119733810425, "target_z": 4.656249744898352, "ce": 6.348263263702393, "genuineness": 4.645420074462891, "identity": 0.8562297821044922, "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_Contentment/77a95aaa5f6a4de854aaf4631d24a6fdc7e945aef185e3c6bcd43618757eafad.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "77bed2388baaae41b81d8c65d17c67447b315449fbf086b60f8e1ffa38c21bd3", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "7acbadf70851f163ae91bedda80f4de04930e25025e75c0eaf049fc55c7c6397", "generation_seconds_batch": 21.892920819926076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.054614543914795, "target_z": 3.3750000147885015, "ce": 6.38797664642334, "genuineness": 4.557555198669434, "identity": 0.5234951972961426, "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_Contentment/77bed2388baaae41b81d8c65d17c67447b315449fbf086b60f8e1ffa38c21bd3.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "780edfe1b97ea613fb9f5fe3ff1dffd24878e898b7c8645d6db485adfd66c62b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "db01626b6256784f6b8b5b7f7bebe4d997b26e912a591b4fd552cc2297fcf57f", "generation_seconds_batch": 19.50856319896411, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9365342855453491, "target_z": 3.140624983362936, "ce": 6.403861999511719, "genuineness": 4.507347106933594, "identity": 0.4935615360736847, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/780edfe1b97ea613fb9f5fe3ff1dffd24878e898b7c8645d6db485adfd66c62b.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "781820f70e0aae6dd9fddbd536a794b248ee1f51b20e6acd1f85b49d2cb899a7", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "33d678c79c04b6c2c526e2e4a685a0bdf99899eae2d6fe0916b337bd47d055d3", "generation_seconds_batch": 20.63832199794706, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.999510407447815, "target_z": 3.2656249685744347, "ce": 6.141753673553467, "genuineness": 4.18099308013916, "identity": 0.787720799446106, "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_Contentment/781820f70e0aae6dd9fddbd536a794b248ee1f51b20e6acd1f85b49d2cb899a7.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "7862428e9cb1daac860754be47489a7cc83c6896afa8841b9232b69bf9232899", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "0c84dd82a9517c2addd4a1890dffb8eec709c9e5ef2baede7dc136f93d9e1ee8", "generation_seconds_batch": 19.55137224297505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.141206741333008, "target_z": 3.5468750536083173, "ce": 6.3641486167907715, "genuineness": 4.337893962860107, "identity": 0.5710753202438354, "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_Contentment/7862428e9cb1daac860754be47489a7cc83c6896afa8841b9232b69bf9232899.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8399340c8274177138e99dc5404b4d0d77d28233976421900d6e1a729c9c7c73", "generation_seconds_batch": 14.346648339997046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8105820417404175, "target_z": 2.890625012939939, "ce": 6.165581703186035, "genuineness": 4.331617832183838, "identity": 0.3644881248474121, "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_Contentment/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.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": "794fb07a79c298c43590673f127b9d2443a720afd1f1e5a176b79b83cc4bedda", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a2bfb36404d17c776139a6f9bd4488ef2cfe7a79857a4415f68aab1174692f20", "generation_seconds_batch": 19.289344487013295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7158639430999756, "target_z": 4.687500096125259, "ce": 6.252951145172119, "genuineness": 3.9173994064331055, "identity": 0.4801371097564697, "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_Contentment/794fb07a79c298c43590673f127b9d2443a720afd1f1e5a176b79b83cc4bedda.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "799fc6638889c3cc3104d2befae76ba99d2a7588bcb2dd5d217ed89fd538d2c0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "553a6d6cb52ac3d71e5cee2227b11212746ad5b0ea048957be20cc5fd9dd28f9", "generation_seconds_batch": 21.9554118210217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.212054967880249, "target_z": 3.68750021443327, "ce": 6.523001670837402, "genuineness": 4.149612903594971, "identity": 0.6853631734848022, "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_Contentment/799fc6638889c3cc3104d2befae76ba99d2a7588bcb2dd5d217ed89fd538d2c0.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "79ab6ded95a656282b74af45756ba1d4b0f4b69ea19b8b978f5ff3e197e6eea5", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9a2ae7ef64b080679fe85c4f756006dca51dea35bea3da41d8f11b82d6083acb", "generation_seconds_batch": 19.60497835604474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.684375762939453, "target_z": 4.6249998669034875, "ce": 6.252951145172119, "genuineness": 4.381826400756836, "identity": 0.7449702024459839, "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_Contentment/79ab6ded95a656282b74af45756ba1d4b0f4b69ea19b8b978f5ff3e197e6eea5.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": "79e5f47e912e96f29068a8173fc5626886d968aee950ce1f052df816041ab25c", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6cbb04c4febc340860c8b455b0f7b13960e2cf0f8f0f745987eabcf2c12af898", "generation_seconds_batch": 14.43368711497169, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.030998468399048, "target_z": 3.3281249611801837, "ce": 6.221180438995361, "genuineness": 4.331617832183838, "identity": 0.3937130570411682, "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_Contentment/79e5f47e912e96f29068a8173fc5626886d968aee950ce1f052df816041ab25c.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": "7a0c574d5882d783b4d73b2270c16ca93a6775053f7fedbb9944a1cbae5ab7c2", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d172d22fe3fbb6dcff99847dec19ec9cda47859cd1afbed77f37eabfda6a572c", "generation_seconds_batch": 19.28625742800068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4009833335876465, "target_z": 4.062500170067765, "ce": 6.1894097328186035, "genuineness": 3.8169827461242676, "identity": 0.4686915874481201, "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_Contentment/7a0c574d5882d783b4d73b2270c16ca93a6775053f7fedbb9944a1cbae5ab7c2.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": "7a51555dc79ab1e5d0099e81eb10eef8ef02f4d6dd1275e7887e83da475b4917", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "4af6356d90cd5c4ce458a761bd8a95c64b03ec5d954acd598387a2085d693da3", "generation_seconds_batch": 14.624484202009626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3380072116851807, "target_z": 3.937500184856267, "ce": 6.078212261199951, "genuineness": 4.3504462242126465, "identity": 0.5807766914367676, "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_Contentment/7a51555dc79ab1e5d0099e81eb10eef8ef02f4d6dd1275e7887e83da475b4917.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "7a754b22ccdaca2224ffcd76ea7cf5569f8fe112e45d43f653106490cbad89ba", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "3abc06c4448ea3b07359fb33c14f52c3509a4168cbce4c7f29c786cca725aa0a", "generation_seconds_batch": 20.931699516950175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.078230619430542, "target_z": 3.421875068396819, "ce": 6.141753673553467, "genuineness": 4.300237655639648, "identity": 0.6844334602355957, "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_Contentment/7a754b22ccdaca2224ffcd76ea7cf5569f8fe112e45d43f653106490cbad89ba.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": "7af59afce98b22823f52f0d33a5ccf03dabaf18fd59cc003d2c9e3bf95f4d472", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "298ce0671af869f52f95dc33607775861fce039352bd431b030e72744882527f", "generation_seconds_batch": 19.72013212798629, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.141206741333008, "target_z": 3.5468750536083173, "ce": 6.0305562019348145, "genuineness": 4.507347106933594, "identity": 0.7456271648406982, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Y avait bien, et vérifié les deux derniers chiffres. Appelle moi quand tu auras un moment.", "wer": 0.13636363636363635, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/7af59afce98b22823f52f0d33a5ccf03dabaf18fd59cc003d2c9e3bf95f4d472.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "7b30d16325c816bf626a2626b4ed1aad9bebe9472503c16cd2b19ee21545bb3d", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "ea9437f87fa27e70bc91b964319f8925367a23cc423ac003142ea4575c20bbff", "generation_seconds_batch": 19.45805310807191, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6686317920684814, "target_z": 4.593749988908624, "ce": 5.919358730316162, "genuineness": 3.773050308227539, "identity": 0.3929920494556427, "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_Contentment/7b30d16325c816bf626a2626b4ed1aad9bebe9472503c16cd2b19ee21545bb3d.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "7b5b1402bb1b95832a47fb6f68921082047d79ac70c1eee25a5ea60a15e2e37c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e464432f0d5dbc98166babd9b9bc769bd95ec72c4d2c6a0d741735924f24c657", "generation_seconds_batch": 14.258004661998712, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.32226300239563, "target_z": 3.9062498336293596, "ce": 6.141753673553467, "genuineness": 4.607763767242432, "identity": 0.6585468053817749, "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_Contentment/7b5b1402bb1b95832a47fb6f68921082047d79ac70c1eee25a5ea60a15e2e37c.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "7bb73a11e1eaba3462767e58ff799aa075e73c98d73f8403e44817a9a8253f89", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1df0941b22417080e1fba2ce36beccd1fc8565c99f49cc30f5e0296eca3fbe5f", "generation_seconds_batch": 19.201237648027018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3537511825561523, "target_z": 3.968750062851131, "ce": 5.895530700683594, "genuineness": 4.080576419830322, "identity": 0.5605528950691223, "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_Contentment/7bb73a11e1eaba3462767e58ff799aa075e73c98d73f8403e44817a9a8253f89.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "7bd549597c15c3cb4ddf10f757d89f0d2edcf604fa19ee34f3b1af9b3b2c410b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "689593c9307dbbadc07282aa0c141d8da59cbfb8ae6c6a86966b0f3735c6f106", "generation_seconds_batch": 14.18425628496334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0939745903015137, "target_z": 3.4531249463916827, "ce": 6.078212261199951, "genuineness": 4.582659721374512, "identity": 0.736481249332428, "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_Contentment/7bd549597c15c3cb4ddf10f757d89f0d2edcf604fa19ee34f3b1af9b3b2c410b.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "7c3e29ba3bb62ee5955500780a43c3c571df17e22d5207b2a01a727c701a385a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "0dfbe0a0b602e7f558f6126be830b357ca9497a40371ad67715f61b89f26f17a", "generation_seconds_batch": 23.14302464807406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6686317920684814, "target_z": 4.593749988908624, "ce": 6.435632705688477, "genuineness": 4.3881025314331055, "identity": 0.30236801505088806, "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_Contentment/7c3e29ba3bb62ee5955500780a43c3c571df17e22d5207b2a01a727c701a385a.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": "7cd869a8bec997a8980276be76809db08f06c7596cbc28b0da8e6140739e1976", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5987795da14a240ebbe9aa01e0d63f4e13f04b39874722e0771d4ecdb795f7c1", "generation_seconds_batch": 20.826781076961197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2907750606536865, "target_z": 3.843750077639632, "ce": 6.38003396987915, "genuineness": 4.193545341491699, "identity": 0.10553794354200363, "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_Contentment/7cd869a8bec997a8980276be76809db08f06c7596cbc28b0da8e6140739e1976.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "7d0f3fdc3f5625c4c045582b2d22c22921ead9b11c097053a3296e83b5018af0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "adc17676c0ea3d14df96c23c5384ba72ea863a53635f37f3660c57313a038ab1", "generation_seconds_batch": 15.202359320945106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4482152462005615, "target_z": 4.156249804052357, "ce": 6.316492557525635, "genuineness": 3.9550557136535645, "identity": 0.4867391586303711, "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_Contentment/7d0f3fdc3f5625c4c045582b2d22c22921ead9b11c097053a3296e83b5018af0.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "7d17a07d488e01ca93f0a9e8715a1f9f077df19e309ea2dc2d73b81b21d9c51f", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d73ec49c564c8809c0fe660bc14ff8f61cb7efd0eabc8b4f9337327e104cc766", "generation_seconds_batch": 20.144021073007025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9601503610610962, "target_z": 3.1875000369712536, "ce": 6.157639026641846, "genuineness": 4.118232727050781, "identity": 0.8197283744812012, "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_Contentment/7d17a07d488e01ca93f0a9e8715a1f9f077df19e309ea2dc2d73b81b21d9c51f.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "7d6208926e8a588891d30d26f3b60c8ad6cdf593fb61576a0a7f7be1b7d6697d", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a14cbc25adb6942a0b5ba49278335fe64bf791e5da642e795021b39a11e727a9", "generation_seconds_batch": 20.345622310996987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2671589851379395, "target_z": 3.7968750240313147, "ce": 6.23706579208374, "genuineness": 4.111956596374512, "identity": 0.24868464469909668, "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_Contentment/7d6208926e8a588891d30d26f3b60c8ad6cdf593fb61576a0a7f7be1b7d6697d.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "7d873ff54f98cd8effe0ba3103ee74357bdcba67532b420bb2fb2d3cf588ea04", "bucket": "emo_Contentment", "phase": "wording", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f7046270b173cbabc995a36027efbbe3ab3245a41e3b86a9d42db159cbe31c50", "generation_seconds_batch": 19.71246002695989, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9050462245941162, "target_z": 3.078124990757187, "ce": 6.324435234069824, "genuineness": 4.3881025314331055, "identity": 0.3673856258392334, "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_Contentment/7d873ff54f98cd8effe0ba3103ee74357bdcba67532b420bb2fb2d3cf588ea04.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "7e3a7ac10882cb5421bf44206c4a76397ad9718d7f3d1150e49805a581086133", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2723a6a151e418373cb2cc39d9ce1bce1e1116672f9e053284a8a6e046883caf", "generation_seconds_batch": 21.735164173995145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.125462770462036, "target_z": 3.5156251756134536, "ce": 6.221180438995361, "genuineness": 4.419482707977295, "identity": 0.34606730937957764, "hypothesis": "De deur staat nog open. Ik heb je Jals 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_Contentment/7e3a7ac10882cb5421bf44206c4a76397ad9718d7f3d1150e49805a581086133.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": "7e4bf10137b6ba0e9343dd2021ac7bb05976c994b05e163a97d7875654902b08", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "792e0dbb47a962eadb3146bb2c00ec48250323d7614b696013b0f7b2053b61ec", "generation_seconds_batch": 19.166526328073815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1569507122039795, "target_z": 3.578124931603181, "ce": 5.974957466125488, "genuineness": 4.519899368286133, "identity": 0.8481566309928894, "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_Contentment/7e4bf10137b6ba0e9343dd2021ac7bb05976c994b05e163a97d7875654902b08.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "7e736738ea94f4f57a8adade0a137b429d324d33041aa223fb715f3d1f093a01", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "a7c886ff96f9c0b245f68a58e52e2812fd94174c1daf8acf1ca1ac22a6f7739c", "generation_seconds_batch": 19.9463481339626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.589911699295044, "target_z": 4.437500125702262, "ce": 6.300607204437256, "genuineness": 4.419482707977295, "identity": 0.7357676029205322, "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_Contentment/7e736738ea94f4f57a8adade0a137b429d324d33041aa223fb715f3d1f093a01.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "7f05848e4efe93bd98955f85e09dd759f02a93c30aed3dc1252ce9479c36c79c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "238b1db90c380afdc97635aec4ab3e06fd07b5d00f9aa51b2923661233500772", "generation_seconds_batch": 20.604053384042345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1729487180709839, "target_z": 1.6249999852114987, "ce": 6.213237762451172, "genuineness": 4.193545341491699, "identity": 0.715661883354187, "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_Contentment/7f05848e4efe93bd98955f85e09dd759f02a93c30aed3dc1252ce9479c36c79c.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "7f1543d4791a6e78cc4ec088759e177ff0227825b2ab29dae3dd1a86f3c4ff21", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "67cf602ac06f65f87936ddd093f45e1a29e8f3a780e429f3385528e1e5b9598a", "generation_seconds_batch": 14.903002227074467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.015254497528076, "target_z": 3.29687508318532, "ce": 6.197352409362793, "genuineness": 4.231201171875, "identity": 0.48037445545196533, "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_Contentment/7f1543d4791a6e78cc4ec088759e177ff0227825b2ab29dae3dd1a86f3c4ff21.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "7f4f7bfc9d7a5893fe41766b4e7d3d6ecc3d70bcc1820f13d0f2b0139a02a246", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d9422a7709d5a8d264d26b3ef387d2704e21ec69e3d64576928e5b614e4e0deb", "generation_seconds_batch": 19.4155606480781, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5584235191345215, "target_z": 4.374999896480491, "ce": 6.078212261199951, "genuineness": 4.306513786315918, "identity": 0.5597277879714966, "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_Contentment/7f4f7bfc9d7a5893fe41766b4e7d3d6ecc3d70bcc1820f13d0f2b0139a02a246.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "ea9e6bae5478c799bdcfc37fd2421c52b6e8e7962ddb9f1c7f4e77f590acf820", "generation_seconds_batch": 14.43830605095718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.369495153427124, "target_z": 3.9999999408459948, "ce": 6.403861999511719, "genuineness": 4.344170093536377, "identity": 0.4584181606769562, "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_Contentment/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.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": "7fc0c84c6d54b9106193328533f4d85a056c754131e5bd78026f3e3546de8a20", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4208e26c6a129d1ebf402e16a2ea1739c562c09dd02a6128149978b5c4d983e0", "generation_seconds_batch": 19.47858167591039, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0467424392700195, "target_z": 3.3593748391750475, "ce": 6.109982967376709, "genuineness": 4.300237655639648, "identity": 0.6055594682693481, "hypothesis": "Quel coin a déplacé la petite chaise bleue? Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/7fc0c84c6d54b9106193328533f4d85a056c754131e5bd78026f3e3546de8a20.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "7fd8fc7428af7c7f87d2a54f36b36007bb54c592de2381cf34ebcafca7b1c347", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a4680b512b91438518e6a27f02f02c39d892e117af1dd334a26acdc2c3fe537d", "generation_seconds_batch": 20.478954209946096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.526935577392578, "target_z": 4.312500140490763, "ce": 6.078212261199951, "genuineness": 4.570107460021973, "identity": 0.8257140517234802, "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_Contentment/7fd8fc7428af7c7f87d2a54f36b36007bb54c592de2381cf34ebcafca7b1c347.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "800afcc5e7a6673af44b342c854a3f304006d342dc5a6f774c4fe310901dff72", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "88d288c1ed7cb2e7e69c6816f0a4fbba8fa3b977f7cbe60ac0b19d4f41be8a99", "generation_seconds_batch": 17.139457298908383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6056556701660156, "target_z": 4.468750003697125, "ce": 6.022613525390625, "genuineness": 4.105680465698242, "identity": 0.4028499722480774, "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_Contentment/800afcc5e7a6673af44b342c854a3f304006d342dc5a6f774c4fe310901dff72.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "80aa2820a94f73e1659341440fcd52795f33057d4cbb86689c510057e9514b5a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7285c25a1020b1914f3027b752ed9a3b9ef46af2bd09ccc39fddf08a1a858809", "generation_seconds_batch": 19.296316997963004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2907750606536865, "target_z": 3.843750077639632, "ce": 6.38003396987915, "genuineness": 4.124508857727051, "identity": 0.5475251078605652, "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_Contentment/80aa2820a94f73e1659341440fcd52795f33057d4cbb86689c510057e9514b5a.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "c7cd4f4ce89787836e185e6527d6042b12078a93dd8a8f3d0fe29fd11e5ed9fb", "generation_seconds_batch": 14.418078035931103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.526935577392578, "target_z": 4.312500140490763, "ce": 6.300607204437256, "genuineness": 4.268857479095459, "identity": 0.46804630756378174, "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_Contentment/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "816618c513a0cb81e8ab4ba4101faf3b1279632177a801b4089e1e07bd5b9dce", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "8186a5d325dd0ca1491b7b97700b3ebc493ded6f4045cbfd420b16b0f6087e2a", "generation_seconds_batch": 19.811024650000036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1690126657485962, "target_z": 1.617187397404772, "ce": 6.213237762451172, "genuineness": 4.457139015197754, "identity": 0.5653510093688965, "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_Contentment/816618c513a0cb81e8ab4ba4101faf3b1279632177a801b4089e1e07bd5b9dce.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "817ac22105e5c76c02505a23985ce58c754b3c25630bdc2f1cec58911a3c7541", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a0a6dd861ee1f598fd0b03c84c9d7ca0a39e8ea698f5c3aa7e02f75f981cf3fd", "generation_seconds_batch": 19.342325179022737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.164822816848755, "target_z": 3.5937501072166347, "ce": 6.4515180587768555, "genuineness": 4.193545341491699, "identity": 0.628786563873291, "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_Contentment/817ac22105e5c76c02505a23985ce58c754b3c25630bdc2f1cec58911a3c7541.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "81dc418d948f1252d57e9fb895263431534bc11e0e46c9afb21099249cf4e04e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "c8a2b81f1fff0fb084ddc30a44514b80586bb16df267794dc2d00630446bc35a", "generation_seconds_batch": 19.394681360921822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2041828632354736, "target_z": 3.6718750388198163, "ce": 6.268836498260498, "genuineness": 3.8295347690582275, "identity": 0.28643175959587097, "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_Contentment/81dc418d948f1252d57e9fb895263431534bc11e0e46c9afb21099249cf4e04e.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "81f713678281f12f5b4d5755aa33bb47aac67a610d7c77a2ae954a5ca3325cd5", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d181e6bceea30933a6bf78b8b263d8ba964f4bf4dead7893cffc993efb699b8d", "generation_seconds_batch": 15.232240288052708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.259286880493164, "target_z": 3.781249848417861, "ce": 6.229123115539551, "genuineness": 4.030367851257324, "identity": 0.5583668947219849, "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_Contentment/81f713678281f12f5b4d5755aa33bb47aac67a610d7c77a2ae954a5ca3325cd5.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "8233926e16c483c4b3ec91607b03c7593694dc55adc735979fc3377c6a128430", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "919c6e8bdc257811dc77d7bc0c0c918cc53a8eae8c68f080824794133591a2fc", "generation_seconds_batch": 19.73517887108028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1333346366882324, "target_z": 3.531249877994864, "ce": 6.173524379730225, "genuineness": 4.21237325668335, "identity": 0.5297707319259644, "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_Contentment/8233926e16c483c4b3ec91607b03c7593694dc55adc735979fc3377c6a128430.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "8242d11be80c44e480346e5913b87be6f254e48cb7aa870db40ec47f0600891e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b4e7189ad6c4e0786b28879011a607df2f3cdb228015407825a7c825f6e6a06e", "generation_seconds_batch": 19.57745108800009, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.589911699295044, "target_z": 4.437500125702262, "ce": 6.141753673553467, "genuineness": 3.998987913131714, "identity": 0.39381861686706543, "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_Contentment/8242d11be80c44e480346e5913b87be6f254e48cb7aa870db40ec47f0600891e.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "8284e038f2a5b7f122bf6b6212687f8938444544939e86069728cee9e322189e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "9877b22ca11f6e6c8701bc11f3274b5f185ed89faa25322d1f0bad93771c011b", "generation_seconds_batch": 24.439234171062708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.54267954826355, "target_z": 4.343750018485626, "ce": 6.24500846862793, "genuineness": 4.344170093536377, "identity": 0.6659107804298401, "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_Contentment/8284e038f2a5b7f122bf6b6212687f8938444544939e86069728cee9e322189e.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "82d31199376400af4a235109bcb975f44271e2f397a4cc39ea3923286b8dcf08", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4726f220fcef46649009939ba07aefc7294d84bfa363754fa179f536765b731a", "generation_seconds_batch": 19.474694291013293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6686317920684814, "target_z": 4.593749988908624, "ce": 6.046441555023193, "genuineness": 4.432034492492676, "identity": 0.8024541139602661, "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_Contentment/82d31199376400af4a235109bcb975f44271e2f397a4cc39ea3923286b8dcf08.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "832fdd30b29a2932972bf7009d4893fa48c57ef59d0e8a8ea4e6637f4e748990", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "83a4e776f4fe13aff7c13c9b46a0e6960aacfd45c89794faf05360a1baaf4e05", "generation_seconds_batch": 21.132584615028463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0231266021728516, "target_z": 3.312500258798774, "ce": 6.181467056274414, "genuineness": 4.375550270080566, "identity": 0.32096290588378906, "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_Contentment/832fdd30b29a2932972bf7009d4893fa48c57ef59d0e8a8ea4e6637f4e748990.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "83b256dc4782407d5e368b04803a6aa7f8ee13795b26763ba7d6b23f08bc88c9", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "68fd71bf63d1714ffdb3b74b8d4f38f09adbf2738e30c1099ecec7dc7060b38d", "generation_seconds_batch": 22.52808667300269, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.369495153427124, "target_z": 3.9999999408459948, "ce": 6.2767791748046875, "genuineness": 4.18099308013916, "identity": 0.20623968541622162, "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_Contentment/83b256dc4782407d5e368b04803a6aa7f8ee13795b26763ba7d6b23f08bc88c9.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": "83f3c9ed29247dc3e847ece4fa6b11258ca5683aff01a84158da691350ba5f05", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e6e5b1363ae0d3e7f942c216ea0f4e78bb486cc23ac6a25f01b52d2552a4571d", "generation_seconds_batch": 14.651468673022464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1963107585906982, "target_z": 3.6562498632063622, "ce": 6.23706579208374, "genuineness": 3.9550557136535645, "identity": 0.3932921290397644, "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_Contentment/83f3c9ed29247dc3e847ece4fa6b11258ca5683aff01a84158da691350ba5f05.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "8483fb0867ac9faedf563983394c072144ae541e17e26f58102504566c4f652c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "936b30e0fd8593d8cc554bc6e35c5cdf8667bc2fd3fbcf0b5e4be1a80ab662a7", "generation_seconds_batch": 19.136294177966192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.212054967880249, "target_z": 3.68750021443327, "ce": 6.213237762451172, "genuineness": 4.118232727050781, "identity": 0.05247863382101059, "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_Contentment/8483fb0867ac9faedf563983394c072144ae541e17e26f58102504566c4f652c.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "84c921e01758340f01d1b73f11b552beeaa6af1f4209c45868d0ef35eb55be7c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "271febd9d3c29cfe773a9f02b9008523758b3bb3d8b8ecf4ffa61d31fa62fc32", "generation_seconds_batch": 20.008611661032774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8418161869049072, "target_z": 4.937500066548256, "ce": 6.252951145172119, "genuineness": 4.13078498840332, "identity": 0.6898171901702881, "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_Contentment/84c921e01758340f01d1b73f11b552beeaa6af1f4209c45868d0ef35eb55be7c.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "84ed13458e1f222dc1334c95d3e2594944f50847dc2fed5c479626e694cc631e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "276560e4d6513c4d3ba0f2717dab6ac031d738e90c471cd6e16158a5399baa69", "generation_seconds_batch": 19.343779332004488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1569507122039795, "target_z": 3.578124931603181, "ce": 6.403861999511719, "genuineness": 4.1998209953308105, "identity": 0.42864710092544556, "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_Contentment/84ed13458e1f222dc1334c95d3e2594944f50847dc2fed5c479626e694cc631e.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": "85065d697c2d96f80d3d3871a89bc142df06b6fba6b242f42a9018499d2236d3", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e2aa7279da943eacc6167bc8069c31d77a36685b99460649668044787f030245", "generation_seconds_batch": 14.570193815976381, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.164822816848755, "target_z": 3.5937501072166347, "ce": 6.229123115539551, "genuineness": 4.482243061065674, "identity": 0.7613215446472168, "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_Contentment/85065d697c2d96f80d3d3871a89bc142df06b6fba6b242f42a9018499d2236d3.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": "856cd566a18bf32a3c916df0cdfbcaee16aecf4114026eb89ffb6be32dade495", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a895c39814abfc5888bf5e1a04e3a4a1a077052624cfd8087a08af2cb1e3ecea", "generation_seconds_batch": 19.47858167591039, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1726949214935303, "target_z": 3.6093752828300887, "ce": 6.213237762451172, "genuineness": 4.419482707977295, "identity": 0.6035341620445251, "hypothesis": "Quelqu'un n'a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/856cd566a18bf32a3c916df0cdfbcaee16aecf4114026eb89ffb6be32dade495.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "85c0933710d487b52677726b4ec6b2ae17c174064c65b45bfde1b3f413eae723", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "4fda4f7d7ceae9e7654152200f7103b221bfe83e75ed28535ad66082a136ce10", "generation_seconds_batch": 19.063470363034867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2671589851379395, "target_z": 3.7968750240313147, "ce": 6.24500846862793, "genuineness": 4.143336772918701, "identity": 0.6051497459411621, "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_Contentment/85c0933710d487b52677726b4ec6b2ae17c174064c65b45bfde1b3f413eae723.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "8641fedc069b6ff58f3c5a792ee62773f3158a1c053ec9defd1d05dd38d4ca78", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e7bf79473c24fd71a14868097f5e7e7ea6aa4a2f9ff38b387c36823f2d9cdef4", "generation_seconds_batch": 19.942965987953357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8971742391586304, "target_z": 3.0625000517597547, "ce": 6.23706579208374, "genuineness": 4.306513786315918, "identity": 0.48669669032096863, "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_Contentment/8641fedc069b6ff58f3c5a792ee62773f3158a1c053ec9defd1d05dd38d4ca78.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "865f5c163febe9a1fc3605155a70cdd0f242fc5c53c98c0bcf7a50917f3fb03a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "8cc9f4209fbc1a51a076c1fc8a15e1de01a08beeaba8d46adb07d996bb9f6573", "generation_seconds_batch": 20.284125469974242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.282902956008911, "target_z": 3.8281249020261785, "ce": 6.300607204437256, "genuineness": 4.281409740447998, "identity": 0.3533359169960022, "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_Contentment/865f5c163febe9a1fc3605155a70cdd0f242fc5c53c98c0bcf7a50917f3fb03a.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": "86982093c24ca92bb18d54b57a7d836c31e2d41c9a8d9892e62daa9ecedc6248", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1e5f129742021462076580b71b536264bce82af35a79837be40316f8da376947", "generation_seconds_batch": 14.429126259987243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.416727304458618, "target_z": 4.093750048062629, "ce": 6.2767791748046875, "genuineness": 4.337893962860107, "identity": 0.7213590741157532, "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_Contentment/86982093c24ca92bb18d54b57a7d836c31e2d41c9a8d9892e62daa9ecedc6248.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "86e6e684358f30ceb09f82383ec9f556bde048bc35e579d8c59bf57fe977da0d", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2e2bfc4e93243e560288e283258d9fc9944cae5eb1593a7ce4e41b4ee3b67d35", "generation_seconds_batch": 21.399024946033023, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6846297979354858, "target_z": 2.6406250425169415, "ce": 6.125868320465088, "genuineness": 4.256305694580078, "identity": 0.6554319858551025, "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_Contentment/86e6e684358f30ceb09f82383ec9f556bde048bc35e579d8c59bf57fe977da0d.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": "88f0e6adf55acb878962a7d1be6f311a951bdf62907e3513c31bfd0029a2d123", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "6182d1067fbac2d439ddbf93bcc34f5150aa6ebc513e3a429585950608e80c12", "generation_seconds_batch": 14.607486602035351, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3301351070404053, "target_z": 3.921875009242813, "ce": 6.268836498260498, "genuineness": 4.381826400756836, "identity": 0.7373825907707214, "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_Contentment/88f0e6adf55acb878962a7d1be6f311a951bdf62907e3513c31bfd0029a2d123.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "89076c44664153057cfe143deb82e94b7008a590dac8d9cd6c28b45f5ef1c608", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ab311d2816fb06acb36ec1bf7dcc6cdc574e05b6a2f384e396eb3b0c5d21390d", "generation_seconds_batch": 19.289671808946878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.164822816848755, "target_z": 3.5937501072166347, "ce": 6.38797664642334, "genuineness": 4.281409740447998, "identity": 0.5761587619781494, "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_Contentment/89076c44664153057cfe143deb82e94b7008a590dac8d9cd6c28b45f5ef1c608.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": "8941bd190c78d9adce8170025bcd8e1d665a8763aac8b528456ba7d10c0eb66f", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a9bbc24aed940e380772ae79ec790b9f791a7ebc10428c24cfdd0f2d193d6d65", "generation_seconds_batch": 14.601529691019095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.259286880493164, "target_z": 3.781249848417861, "ce": 6.356205940246582, "genuineness": 4.381826400756836, "identity": 0.6251144409179688, "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_Contentment/8941bd190c78d9adce8170025bcd8e1d665a8763aac8b528456ba7d10c0eb66f.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": "8948aa9d7ecfe8612b4af1fca9918b2ecc3ef9bc44860e96c68d3c5d37e3f274", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "1fbcad4820fa21de4ae92e21032f0e5fcc4243660648b3f16965c4f9a3163b66", "generation_seconds_batch": 14.634125599986874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.526935577392578, "target_z": 4.312500140490763, "ce": 6.252951145172119, "genuineness": 4.457139015197754, "identity": 0.6515246629714966, "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_Contentment/8948aa9d7ecfe8612b4af1fca9918b2ecc3ef9bc44860e96c68d3c5d37e3f274.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "8951e24703b9c250d6ca7ca34ab3b9773c0e0c598cd1fb377270bbdf948bdec5", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d4136541dd768f75c0fabfa43e8ec2551051bdf1efb9d24466438af2ecea4bb3", "generation_seconds_batch": 14.346214115968905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.574167490005493, "target_z": 4.406249774475354, "ce": 6.268836498260498, "genuineness": 4.406930446624756, "identity": 0.3584243655204773, "hypothesis": "I found the little box. It was beside the OOOD 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_Contentment/8951e24703b9c250d6ca7ca34ab3b9773c0e0c598cd1fb377270bbdf948bdec5.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "8a2b09d6a9b0ede8598cfce5d07a449124280b867daf1aab323ded352e85156e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ff4a3389e8fecdf6b62476e8c0a790a6c8ff2c98e61aff94ee3bbd20d7b31f34", "generation_seconds_batch": 14.879864010028541, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.747351884841919, "target_z": 4.749999852114986, "ce": 6.125868320465088, "genuineness": 3.9676074981689453, "identity": 0.35567378997802734, "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_Contentment/8a2b09d6a9b0ede8598cfce5d07a449124280b867daf1aab323ded352e85156e.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "8a977ed007c955d9f58106aca4bfbf6d510235307c641b3c16e797f12ac90ec3", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2b161beb247b6afe0aa9efbcfc42bfd811845cfee9c6439f137da9d1b50200be", "generation_seconds_batch": 19.615125727956183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.235671043395996, "target_z": 3.734375268041587, "ce": 6.0146708488464355, "genuineness": 4.482243061065674, "identity": 0.810809850692749, "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_Contentment/8a977ed007c955d9f58106aca4bfbf6d510235307c641b3c16e797f12ac90ec3.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "8b03969930088e59281eb6af59f4e9d2896054387fcc7e6e139297cf4e8c82ed", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a80703a94bc4d41fc40debd7103d2047ef6dd24c2ce2af3f2d427011d1e3bb68", "generation_seconds_batch": 19.57667818502523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.235671043395996, "target_z": 3.734375268041587, "ce": 6.117925643920898, "genuineness": 4.406930446624756, "identity": 0.7159629464149475, "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_Contentment/8b03969930088e59281eb6af59f4e9d2896054387fcc7e6e139297cf4e8c82ed.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "8b2208717135f59d9688d487ce4ad057abcfe766977e91db357c8d49cc336166", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d45326ba419ae5ad5f23f2c47e3723fc41bd726ff41909ba8035dbf875f68017", "generation_seconds_batch": 19.608696948038414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3616230487823486, "target_z": 3.9843747652325407, "ce": 6.125868320465088, "genuineness": 4.218649387359619, "identity": 0.6268711090087891, "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_Contentment/8b2208717135f59d9688d487ce4ad057abcfe766977e91db357c8d49cc336166.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "8b96727ea1f0df6512b64b318624e63dfe2628d25bfd50f7078ae9afcbc4dabd", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "4ea436307203b6c4f8479155ba93b812910a6eb46a1710948de6f02d9fd53ffc", "generation_seconds_batch": 22.183091050945222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1963107585906982, "target_z": 3.6562498632063622, "ce": 6.332377910614014, "genuineness": 4.68307638168335, "identity": 0.8525987863540649, "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_Contentment/8b96727ea1f0df6512b64b318624e63dfe2628d25bfd50f7078ae9afcbc4dabd.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "8bbae113d519b3af7155f014dc2d3fa568a4927300c485ec4adb37aab1d64fb0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b892d6ad2147fceafcef89c4a4b0e05455eca9a67e00e8d9f7bcb79b0d221202", "generation_seconds_batch": 19.987298988969997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5035734176635742, "target_z": 2.2812500258798774, "ce": 6.213237762451172, "genuineness": 4.331617832183838, "identity": 0.5527958869934082, "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_Contentment/8bbae113d519b3af7155f014dc2d3fa568a4927300c485ec4adb37aab1d64fb0.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "8c53ca57bd2e3b093f14137a42c8facef5f0ca0e0104a9fba5a4220bdf868e80", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "3fb6d4f811772a115f64cd325a74b6da282e5a615dc841fc1feae25a1cb5932d", "generation_seconds_batch": 14.973213821067475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5584235191345215, "target_z": 4.374999896480491, "ce": 6.0305562019348145, "genuineness": 4.030367851257324, "identity": 0.5044769644737244, "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_Contentment/8c53ca57bd2e3b093f14137a42c8facef5f0ca0e0104a9fba5a4220bdf868e80.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "8c6b7ee8d527835fff5b2b6390760af07024ea1dd074a7e46eeb70b3f1a65e23", "bucket": "emo_Contentment", "phase": "wording", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "5c6722c1232f5c472efc61abb52ebe83ab1b314eb144427f740a25059c1c911d", "generation_seconds_batch": 18.151324541890062, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.054614543914795, "target_z": 3.3750000147885015, "ce": 6.340320587158203, "genuineness": 4.036643981933594, "identity": 0.5181996822357178, "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_Contentment/8c6b7ee8d527835fff5b2b6390760af07024ea1dd074a7e46eeb70b3f1a65e23.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "8c757544a3c13c197eed5958c7cedd808e81e62eafecea72727b94fcf41ed81e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "7b8467fab8cbb4e6f0d730a5ecce5638ac66f87c53307fa86157f7f828b403ad", "generation_seconds_batch": 20.027965874993242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.275031089782715, "target_z": 3.8125001996447683, "ce": 6.3641486167907715, "genuineness": 4.256305694580078, "identity": 0.67042076587677, "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_Contentment/8c757544a3c13c197eed5958c7cedd808e81e62eafecea72727b94fcf41ed81e.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "8c7bb53766116294747b90d284b9d1bd3c38568ca327077135f987970a3a64ef", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "40c533c8f1e19091c75903903a19ad559feb0ae24bf6aa02304a08aa5a5b6149", "generation_seconds_batch": 23.089647065033205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9286623001098633, "target_z": 3.125000044365504, "ce": 6.221180438995361, "genuineness": 4.168440818786621, "identity": 0.7729123830795288, "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_Contentment/8c7bb53766116294747b90d284b9d1bd3c38568ca327077135f987970a3a64ef.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": "8c816907bcb3cf8e05d8516acdce3ffa213960fff96d646f89f0fc62cd9924e2", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Escribí el número en el sobre.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "14a08da0b53fb6eaa2a0c0b484566659b77536072d3b93b34ff3375ec04174ea", "generation_seconds_batch": 19.389432864030823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6056556701660156, "target_z": 4.468750003697125, "ce": 6.23706579208374, "genuineness": 4.162164688110352, "identity": 0.6753911375999451, "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_Contentment/8c816907bcb3cf8e05d8516acdce3ffa213960fff96d646f89f0fc62cd9924e2.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "8cef03ce43836e6310edff6a42ab50b91738a8fb12d5860af3ec1b38adf17816", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "702156466bc84cef768b79c4f49ac8f839ebe045b096392170d0fbd8ffad7681", "generation_seconds_batch": 19.923084749956615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2671589851379395, "target_z": 3.7968750240313147, "ce": 6.308549880981445, "genuineness": 4.337893962860107, "identity": 0.7674314975738525, "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_Contentment/8cef03ce43836e6310edff6a42ab50b91738a8fb12d5860af3ec1b38adf17816.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "8d16c7438532f3cc89ed0b51ec0c5f32ae7a43d5cba5954d22059d49e6de4f0c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "7ed6d9517f6eb3d471ae2b406d6b568b38bbcf59189f75c5f1ebdf939ccb5aac", "generation_seconds_batch": 19.849573559011333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2199268341064453, "target_z": 3.70312491681468, "ce": 6.24500846862793, "genuineness": 3.8420867919921875, "identity": 0.2084435075521469, "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_Contentment/8d16c7438532f3cc89ed0b51ec0c5f32ae7a43d5cba5954d22059d49e6de4f0c.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "8d3340ee24968e2d177dc0559401429468bdb074446e59279987a5780028c30d", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "7e01e556382a87ee0fe184d0a42d3a33e25e0ce629dab31ba12b0e3a72f246d1", "generation_seconds_batch": 21.562214985024184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0703585147857666, "target_z": 3.4062498927833653, "ce": 6.260893821716309, "genuineness": 3.9550557136535645, "identity": 0.5539714694023132, "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_Contentment/8d3340ee24968e2d177dc0559401429468bdb074446e59279987a5780028c30d.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": "8d47ed885eff97c1a273b9e6bb4acefc0113a13e5afa0a581c5208930285a41e", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ff56282165ca24a198144b485ef5ffca88c8f4c1635c6b13f61300e3ac5df0fd", "generation_seconds_batch": 19.166526328073815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3852391242980957, "target_z": 4.031249818840858, "ce": 6.181467056274414, "genuineness": 4.457139015197754, "identity": 0.7230968475341797, "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_Contentment/8d47ed885eff97c1a273b9e6bb4acefc0113a13e5afa0a581c5208930285a41e.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "8d7ded6b15f4994e5bab6439175e9bda4798cbc47cbb4801eefc3e0207533a07", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "9faeb36ea91b5ed93bcdf39833b387d4b4117caa4dfc71b9679e113e3b0fd6c5", "generation_seconds_batch": 19.227762209018692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.700119733810425, "target_z": 4.656249744898352, "ce": 6.316492557525635, "genuineness": 4.319066047668457, "identity": 0.42170968651771545, "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_Contentment/8d7ded6b15f4994e5bab6439175e9bda4798cbc47cbb4801eefc3e0207533a07.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "8dc6301668e9cf590999708207de48b2171b7306dc9fce1b09c84a1067ace033", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "4f247619616ce943458e388afbbf8ab3ba46a5af873fdb357435aaee91d89f48", "generation_seconds_batch": 19.248446488985792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1963107585906982, "target_z": 3.6562498632063622, "ce": 6.300607204437256, "genuineness": 4.375550270080566, "identity": 0.4588008522987366, "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_Contentment/8dc6301668e9cf590999708207de48b2171b7306dc9fce1b09c84a1067ace033.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": "8e38c5a4a4f75c8a91b0c4862c44288343d9dc94554f49d317f730d800b3f104", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Escribí el número en el sobre.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "74adde4c296988f4a9db1d0ab1d358c0a6579d13c6ae03943415adc7a705f053", "generation_seconds_batch": 14.375520672998391, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6213996410369873, "target_z": 4.4999998816919895, "ce": 6.062326908111572, "genuineness": 4.306513786315918, "identity": 0.6364220380783081, "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_Contentment/8e38c5a4a4f75c8a91b0c4862c44288343d9dc94554f49d317f730d800b3f104.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "8ed3ec16ae0294106fc89e6650dd7fc57f1910c1dbef5bf6bea4a85fd41ee1ee", "bucket": "emo_Contentment", "phase": "wording", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c67884240b3b8c4cbfa9ab961064c7d90ac99d82bdff109183d0ef115bb83413", "generation_seconds_batch": 15.907818280044012, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.54267954826355, "target_z": 4.343750018485626, "ce": 6.181467056274414, "genuineness": 4.406930446624756, "identity": 0.5886342525482178, "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_Contentment/8ed3ec16ae0294106fc89e6650dd7fc57f1910c1dbef5bf6bea4a85fd41ee1ee.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "8f114ebf5cf8b244c34f5a553887eec2bba6b6e8dd447b472a87b18bdf236061", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "de27701beab0bbe7f360fda7674c8c6a4b0fb9c3b9c7412046ce347f776398f6", "generation_seconds_batch": 20.518324925913475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4482152462005615, "target_z": 4.156249804052357, "ce": 6.149696350097656, "genuineness": 4.011539936065674, "identity": 0.7001489400863647, "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_Contentment/8f114ebf5cf8b244c34f5a553887eec2bba6b6e8dd447b472a87b18bdf236061.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "8f3945464f68f99b94806dd81edf6883b10863a5241a865f17797a1db021c19e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b5e5747ab6188decf78369cee80961f7afc33cf30f583665df8fd9cacd5243ee", "generation_seconds_batch": 19.929894761997275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1726949214935303, "target_z": 3.6093752828300887, "ce": 6.292664527893066, "genuineness": 4.080576419830322, "identity": 0.4924572706222534, "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_Contentment/8f3945464f68f99b94806dd81edf6883b10863a5241a865f17797a1db021c19e.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "8f8c987eaad9daff0690647f5d0bb915eeff2b513f34431a35a712aa6427d3f5", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d825864fae9fa5ae5a167469cf5ec2436817d479250d8696402fe381501b7048", "generation_seconds_batch": 20.47220836696215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.345879077911377, "target_z": 3.953124887237677, "ce": 6.260893821716309, "genuineness": 4.337893962860107, "identity": 0.4942629933357239, "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_Contentment/8f8c987eaad9daff0690647f5d0bb915eeff2b513f34431a35a712aa6427d3f5.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "8fa083e7c90c9bbae94529cc57e6385a7fb06496996aa9e508a26d4279ccbd74", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c90f31aba9cd5918b411adafe3189bde7c96f12a0b8ed027b4bf84275b02f035", "generation_seconds_batch": 14.258004661998712, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4954473972320557, "target_z": 4.249999911268992, "ce": 6.181467056274414, "genuineness": 4.20609712600708, "identity": 0.6807518005371094, "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_Contentment/8fa083e7c90c9bbae94529cc57e6385a7fb06496996aa9e508a26d4279ccbd74.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "905545998c07bf06e7c5a1a5c0f15ed4426899fea8c874b21decd0d7ebb96457", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "5816ba81705c2a23bc9f9d6578b8a0b6d429731662468dd046d716f5cdf675f2", "generation_seconds_batch": 19.90394168207422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5111913681030273, "target_z": 4.281249789263856, "ce": 6.046441555023193, "genuineness": 3.8671910762786865, "identity": 0.4905467927455902, "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_Contentment/905545998c07bf06e7c5a1a5c0f15ed4426899fea8c874b21decd0d7ebb96457.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "906420327ecd70f494a303786e8557715cbbd38c7adc4a6b76d78a07dee4d9bb", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "44211404a213fb2730bd90eea01223db853e2a83a21d40a952f0c2cb45e6a6a4", "generation_seconds_batch": 20.17170429509133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0703585147857666, "target_z": 3.4062498927833653, "ce": 6.38003396987915, "genuineness": 3.986435890197754, "identity": 0.5857423543930054, "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_Contentment/906420327ecd70f494a303786e8557715cbbd38c7adc4a6b76d78a07dee4d9bb.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "9127f599c507d762a01284ca08dbae4887a019343fc2eba47ad134db19b57e7a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "078585269c890f9919a789644fc923efb00495a5e4c67f20b3640cf01adbb7f9", "generation_seconds_batch": 19.846119016990997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9286623001098633, "target_z": 3.125000044365504, "ce": 6.197352409362793, "genuineness": 4.2249250411987305, "identity": 0.69451904296875, "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_Contentment/9127f599c507d762a01284ca08dbae4887a019343fc2eba47ad134db19b57e7a.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "91f0d41749b83a16f7b13242bb43609c034f9e16d77d2ebd0325a23dfcd6336f", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "c336512e835dae951fc26a8c8bb4e1c2d22f7cdb6280943709abe30536349106", "generation_seconds_batch": 20.221746916067787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3616230487823486, "target_z": 3.9843747652325407, "ce": 6.41180419921875, "genuineness": 4.369274139404297, "identity": 0.5266710519790649, "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_Contentment/91f0d41749b83a16f7b13242bb43609c034f9e16d77d2ebd0325a23dfcd6336f.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "924a7324a12828d6b7ddc1a6d7503540f4a13e46aa27c68c4561531abf040949", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "24ebb3a606fd1296f659086371c4be21f48dc9e7f62c096f571d149d8550a041", "generation_seconds_batch": 16.582272604922764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4954473972320557, "target_z": 4.249999911268992, "ce": 6.070269584655762, "genuineness": 4.137060642242432, "identity": 0.6546424031257629, "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_Contentment/924a7324a12828d6b7ddc1a6d7503540f4a13e46aa27c68c4561531abf040949.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "92faf72988dbd2f33c228b86993ceae53b4f77c8c2aba72f9ea8fede3ee70db9", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "8631da11c401b024c58ea5e5251ae41dca72ff26c89710c126bf9af49fde992e", "generation_seconds_batch": 19.914938758010976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4482152462005615, "target_z": 4.156249804052357, "ce": 6.284721851348877, "genuineness": 3.785602569580078, "identity": 0.14845535159111023, "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_Contentment/92faf72988dbd2f33c228b86993ceae53b4f77c8c2aba72f9ea8fede3ee70db9.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "931c93bf0f8e5b5d520a1d532e551832f2f788d8aaa6f9e82c005f106edea5d1", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d1a0f63c582a7463f4fb97fb75c81d00fba0fde5c6137615b962babd41daab04", "generation_seconds_batch": 23.98244228796102, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5111913681030273, "target_z": 4.281249789263856, "ce": 6.300607204437256, "genuineness": 4.319066047668457, "identity": 0.3373658061027527, "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_Contentment/931c93bf0f8e5b5d520a1d532e551832f2f788d8aaa6f9e82c005f106edea5d1.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": "936521ee814a392b14823cffd78aa4897d97a46701daa8a4ada0b48fe07180a3", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "9390eb3044e71183805877e59190cdd31e95fd0fdd98f48cf8787c119f33bd64", "generation_seconds_batch": 14.722495881957002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1175906658172607, "target_z": 3.5, "ce": 6.284721851348877, "genuineness": 4.093128204345703, "identity": 0.6349934339523315, "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_Contentment/936521ee814a392b14823cffd78aa4897d97a46701daa8a4ada0b48fe07180a3.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": "9371f0751eab03892fc2aa7a36ae88ade7e2739064aac6cd0571ae602507c433", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The keys are on the kitchen table.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "783d5c5adaef271ee7f618f2dda0572502ad556374629ddea55bdcac1dab282a", "generation_seconds_batch": 14.495483485981822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.479703426361084, "target_z": 4.218750033274128, "ce": 6.372091293334961, "genuineness": 4.231201171875, "identity": 0.3376663625240326, "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_Contentment/9371f0751eab03892fc2aa7a36ae88ade7e2739064aac6cd0571ae602507c433.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "9442ae935e596abb51ce95bcdf63b87c789539c63d88b9adc89be036739bbb13", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "3eddcf95dc2e8f1146057051cb9ea31a7783d93259e4f5319af580737dfece5c", "generation_seconds_batch": 19.227762209018692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6056556701660156, "target_z": 4.468750003697125, "ce": 6.324435234069824, "genuineness": 4.2751336097717285, "identity": 0.4057767391204834, "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_Contentment/9442ae935e596abb51ce95bcdf63b87c789539c63d88b9adc89be036739bbb13.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "94a67622b0ff0b83b67a9179df8ed9bafd7d71cb6c1a6100c963aaa6e08e4e7e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2bb6ad2192af3bc593a7140f6ea002c742cddfb40443fee1e68b0cc62fe26d88", "generation_seconds_batch": 14.408623041003011, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3616230487823486, "target_z": 3.9843747652325407, "ce": 5.649308204650879, "genuineness": 3.810706615447998, "identity": 0.46365267038345337, "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_Contentment/94a67622b0ff0b83b67a9179df8ed9bafd7d71cb6c1a6100c963aaa6e08e4e7e.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": "94b07be9d7c17896edcd326cf2476a739c277252ce52bb7b62eabe22a6422161", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Someone moved the little blue chair.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "944b490fed1d9abfc8ab6333acc43a7320a5b91de44b751e9623f9f6fff409b9", "generation_seconds_batch": 14.739135493990034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4639594554901123, "target_z": 4.187500155279264, "ce": 6.38003396987915, "genuineness": 4.18726921081543, "identity": 0.4468032419681549, "hypothesis": "Someone moved the little blue chair. It used to stand here b beside the tall bookshelf. We can put it back after lunch.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/94b07be9d7c17896edcd326cf2476a739c277252ce52bb7b62eabe22a6422161.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": "9509ecda9043e1861d9b318bd79c909a8b654cf80fc1ec90069efe4a9cadd4f0", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I wrote the number on the envelope.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "32695c11f7ef784f5da47f50f04f5bca556a83f60073648bb6ad267bc3f12209", "generation_seconds_batch": 14.54715107800439, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3380072116851807, "target_z": 3.937500184856267, "ce": 6.443574905395508, "genuineness": 3.9425034523010254, "identity": 0.33553317189216614, "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_Contentment/9509ecda9043e1861d9b318bd79c909a8b654cf80fc1ec90069efe4a9cadd4f0.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "95efac2fef57c6b74552c27adee7ff9c8519093ab5a6b239ec894ed912c35741", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "5d99d54686c001bc4e7cfbc610bc72706825410dcc4e2932c11cdb79252eccae", "generation_seconds_batch": 19.476461504003964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4009833335876465, "target_z": 4.062500170067765, "ce": 6.268836498260498, "genuineness": 4.381826400756836, "identity": 0.5008838176727295, "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_Contentment/95efac2fef57c6b74552c27adee7ff9c8519093ab5a6b239ec894ed912c35741.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "97e184fd4762ce95184142c2a8a00dc16b3d765e42ae22f34c540d5015c93e06", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "1d1744456fe3de983f3322c12e2f263a2dfe67190049a4e40a9cddbda750e43d", "generation_seconds_batch": 22.183091050945222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.275031089782715, "target_z": 3.8125001996447683, "ce": 6.340320587158203, "genuineness": 4.532451152801514, "identity": 0.6615565419197083, "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_Contentment/97e184fd4762ce95184142c2a8a00dc16b3d765e42ae22f34c540d5015c93e06.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "97ef05921b1fe847bc3542c4237887439ae906274c81b82cef6d4bb3450602ce", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ccafa1687992b8f241b71f0afe0b27ae9cc219773355997dfcc1056e28ceb9c2", "generation_seconds_batch": 19.43443990999367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3852391242980957, "target_z": 4.031249818840858, "ce": 5.661221981048584, "genuineness": 3.998987913131714, "identity": 0.3890819549560547, "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_Contentment/97ef05921b1fe847bc3542c4237887439ae906274c81b82cef6d4bb3450602ce.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "98a906707649c138873ef66d971c60dce8e2d6bbccc0c97443f548e75615c6c0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "68edf1c9bd4ae40a5362594a07664ab39fa4a101ca91fad94ba75a8420517e3f", "generation_seconds_batch": 23.744477748987265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.259286880493164, "target_z": 3.781249848417861, "ce": 6.133810997009277, "genuineness": 4.231201171875, "identity": 0.4892161786556244, "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_Contentment/98a906707649c138873ef66d971c60dce8e2d6bbccc0c97443f548e75615c6c0.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "98d85a329f76f6479e5286b12d338cdeb0401d6b9b4990bf2962a96a996a2911", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "11332990cab5f59373b2a02f547375a982f87fe470856801b802b8127dbc1f1f", "generation_seconds_batch": 20.144021073007025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1569507122039795, "target_z": 3.578124931603181, "ce": 6.260893821716309, "genuineness": 4.3127899169921875, "identity": 0.5458732843399048, "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_Contentment/98d85a329f76f6479e5286b12d338cdeb0401d6b9b4990bf2962a96a996a2911.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "995abe0c5e26337abc50e0abd6c95684ad8b26808fea425e42f5b47ef4d94905", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f25c47cef4a858e997cd6937d65b8b7d4342208324678745333f17b6cbd4bbee", "generation_seconds_batch": 15.232240288052708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9601503610610962, "target_z": 3.1875000369712536, "ce": 6.300607204437256, "genuineness": 4.582659721374512, "identity": 0.6249299049377441, "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_Contentment/995abe0c5e26337abc50e0abd6c95684ad8b26808fea425e42f5b47ef4d94905.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": "99992da6ec3206db788a0764570d4123bf7eb03b284eeb8e0fdeb1e2c7ed61c5", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5d136e5091fb7e4affe3cb4a5f8aa29d3135bd16a2845131cbc930b4cba53dfa", "generation_seconds_batch": 14.507397134089842, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.999510407447815, "target_z": 3.2656249685744347, "ce": 6.467403411865234, "genuineness": 4.432034492492676, "identity": 0.5081812143325806, "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_Contentment/99992da6ec3206db788a0764570d4123bf7eb03b284eeb8e0fdeb1e2c7ed61c5.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "99b0352d1c309b0dbf22caafbd660a85944febb780257e651d69f573aa7355cf", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fafcdc7ea79f6baf0249b096c9edfd511a93c6d80c8ba9ef1d54af66c987877f", "generation_seconds_batch": 20.454924631980248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1963107585906982, "target_z": 3.6562498632063622, "ce": 6.348263263702393, "genuineness": 4.444586753845215, "identity": 0.7504833936691284, "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_Contentment/99b0352d1c309b0dbf22caafbd660a85944febb780257e651d69f573aa7355cf.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "fe861b5250acd2f724caf5a27d8dd555bcbaed50abae34803c70358803e4fc50", "generation_seconds_batch": 16.532820568885654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.62165367603302, "target_z": 2.5156250573054426, "ce": 6.475345611572266, "genuineness": 4.406930446624756, "identity": 0.5153185129165649, "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_Contentment/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "9a07326b695906ee38711f130b0ef07a13d49bf3713cf973a27749ba26945554", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "611118b7324203ccca0b39c22d5ad298e30cec70556eb255e6ee91208b436c7a", "generation_seconds_batch": 19.27987823006697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5111913681030273, "target_z": 4.281249789263856, "ce": 6.2767791748046875, "genuineness": 4.3504462242126465, "identity": 0.3218050003051758, "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_Contentment/9a07326b695906ee38711f130b0ef07a13d49bf3713cf973a27749ba26945554.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "9a5f47a12ef0634d1bf648a3edb078c5d99c352a163f54673c66a2e20dc825af", "bucket": "emo_Contentment", "phase": "wording", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "59f5d3b9cdc772c5bf182500a0e538959687d0494764e419ede420451a965a40", "generation_seconds_batch": 15.907818280044012, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.526935577392578, "target_z": 4.312500140490763, "ce": 6.292664527893066, "genuineness": 4.519899368286133, "identity": 0.6025352478027344, "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_Contentment/9a5f47a12ef0634d1bf648a3edb078c5d99c352a163f54673c66a2e20dc825af.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "9b629ce0f4e14971b7ee87313b7eb7fd804a5edb71692e9dd7d5704ebc82f27e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d09a59f0beae85885a3a363a0242d37f88721cd01149acaecd870a4b36e0cf3e", "generation_seconds_batch": 20.465708237024955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1805667877197266, "target_z": 3.6249999852114985, "ce": 6.308549880981445, "genuineness": 4.005263805389404, "identity": 0.49388670921325684, "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_Contentment/9b629ce0f4e14971b7ee87313b7eb7fd804a5edb71692e9dd7d5704ebc82f27e.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "9bb69c0f4c59d27f3c182d5b99f14e1022df3e031af88eb3f12ca1fb7e19cc7b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a25054f89adf0d0a7afd11f99071d8826e0fa93e56764c5c41741b6a075f7fd9", "generation_seconds_batch": 19.85247933201026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8260719776153564, "target_z": 4.906249715321349, "ce": 6.23706579208374, "genuineness": 4.331617832183838, "identity": 0.5777287483215332, "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_Contentment/9bb69c0f4c59d27f3c182d5b99f14e1022df3e031af88eb3f12ca1fb7e19cc7b.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "9bf0d2734b9812c91ce5950f26d5ab8993177d557607f406a2086170f84971de", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "49a5da471b42c30ce2ffbdb65ca2ae346a66afe69eae0a9d026cd6a05b0fda7e", "generation_seconds_batch": 19.77650257491041, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0388705730438232, "target_z": 3.3437501367936378, "ce": 5.974957466125488, "genuineness": 4.061748504638672, "identity": 0.705204427242279, "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_Contentment/9bf0d2734b9812c91ce5950f26d5ab8993177d557607f406a2086170f84971de.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4ef9c434a656d287dd13e1985d96ed99de91aa0ff30613ed8497b050b56f99fa", "generation_seconds_batch": 14.355021241935901, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.999510407447815, "target_z": 3.2656249685744347, "ce": 6.24500846862793, "genuineness": 4.457139015197754, "identity": 0.6535607576370239, "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_Contentment/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "9c15708dda252d99b5fa395f963dd304a18c10eb7f710cd95248a6dd94fbfbf6", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "987f1635a892e51b9d24943b3cf40f4852007afb8976d2c9f676c5a5f7fcb6ad", "generation_seconds_batch": 14.441985199926421, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.345879077911377, "target_z": 3.953124887237677, "ce": 6.1894097328186035, "genuineness": 4.432034492492676, "identity": 0.6909525394439697, "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_Contentment/9c15708dda252d99b5fa395f963dd304a18c10eb7f710cd95248a6dd94fbfbf6.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "df25c8bd2af1676879842b527f2f18c68f2bfa0c49e29ef0ade454d4ee1f8aed", "generation_seconds_batch": 14.422055994044058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.015254497528076, "target_z": 3.29687508318532, "ce": 5.998785495758057, "genuineness": 4.218649387359619, "identity": 0.5220682621002197, "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_Contentment/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.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": "9cb380b744cdea516b19ff6be93e76968a18afd4045bb1851d35135664ff37e7", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "844589f3acb59e519c5ff3bed2f07d392a8b88806021c88f22f9ba8cb45886be", "generation_seconds_batch": 19.417256820946932, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6056556701660156, "target_z": 4.468750003697125, "ce": 6.181467056274414, "genuineness": 4.093128204345703, "identity": 0.6701851487159729, "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_Contentment/9cb380b744cdea516b19ff6be93e76968a18afd4045bb1851d35135664ff37e7.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": "9ccb88a2404aace58c8a308dc3c457e796c915c0921b9a45f0f49283d358b624", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eb74170dcd6d1fd2dba27f1504d3b6f381a8a7087d3866838c33f5bee537c18c", "generation_seconds_batch": 14.449652798939496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6528878211975098, "target_z": 4.56250011091376, "ce": 6.23706579208374, "genuineness": 4.137060642242432, "identity": 0.7756273150444031, "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_Contentment/9ccb88a2404aace58c8a308dc3c457e796c915c0921b9a45f0f49283d358b624.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": "9ccbc1dad8939847c132da33e27bfd376693fc1629f23f797d6b678c04c60ba2", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a13aec54de2999a58eeecf57e3948dbf365c105b4440bb26d90da07040237a81", "generation_seconds_batch": 14.664150257012807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.479703426361084, "target_z": 4.218750033274128, "ce": 6.125868320465088, "genuineness": 4.105680465698242, "identity": 0.5658223628997803, "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_Contentment/9ccbc1dad8939847c132da33e27bfd376693fc1629f23f797d6b678c04c60ba2.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "9cef086038803f41dd549874e343a7af74196e79b2b2ccd9c1c8a5959241e9dc", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "4282c7bc5c073d1892f865c88aaea6d537ecacce2c75fe7cc3e897629cd9e5a3", "generation_seconds_batch": 24.36600613698829, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.54267954826355, "target_z": 4.343750018485626, "ce": 6.141753673553467, "genuineness": 4.400654315948486, "identity": 0.7569417357444763, "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_Contentment/9cef086038803f41dd549874e343a7af74196e79b2b2ccd9c1c8a5959241e9dc.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "9d45aea6bba449f0492ab7c627e55dd519f0e0b29fdc7411534e5f2580d3bcf0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "1868e71eae6c4f01588b189d4746967a3fa2fd1ae5c8d961791acc641ec2d2fc", "generation_seconds_batch": 14.877906944020651, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1097185611724854, "target_z": 3.4843748243865464, "ce": 6.2767791748046875, "genuineness": 4.306513786315918, "identity": 0.7008740901947021, "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_Contentment/9d45aea6bba449f0492ab7c627e55dd519f0e0b29fdc7411534e5f2580d3bcf0.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "9d86a8265e9c4f3088a6e57805adf426bbd17a18dc91fc4a58ed752ba3fee255", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "728c612fd3c9cf222f1f6986d41153f086f3505b7628c184200dfab4692bc69d", "generation_seconds_batch": 19.452995316009037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4954473972320557, "target_z": 4.249999911268992, "ce": 6.24500846862793, "genuineness": 4.325342178344727, "identity": 0.4454096555709839, "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_Contentment/9d86a8265e9c4f3088a6e57805adf426bbd17a18dc91fc4a58ed752ba3fee255.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "9df3a19a8d6ae91810db8bc5a117cd21b73be0bbc80433885507d67a27fa8e43", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "7761f512d7503929e3b004277b15233ac00130b0bf2f7980a4e316a5eb65d03a", "generation_seconds_batch": 19.849573559011333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1175906658172607, "target_z": 3.5, "ce": 6.356205940246582, "genuineness": 4.074300289154053, "identity": 0.24417421221733093, "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_Contentment/9df3a19a8d6ae91810db8bc5a117cd21b73be0bbc80433885507d67a27fa8e43.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "9e4a138c129434748e032ce0d540ede8ab4b5126c664f043e2cecfbba783f6be", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "3f9bcc792e9d388ef89a0eba6c4f117b3e791593f2f44a4bbcb7abd428abce01", "generation_seconds_batch": 16.29015353298746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.479703426361084, "target_z": 4.218750033274128, "ce": 6.2767791748046875, "genuineness": 4.105680465698242, "identity": 0.2409801185131073, "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_Contentment/9e4a138c129434748e032ce0d540ede8ab4b5126c664f043e2cecfbba783f6be.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "9f510dbdcf5a5ccc5229ca8d0c1a65cd6e452c619a7a010ef2c7e3bae2142d3b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "cd97691506d610d370698123966cb22e86b53e2a0c31706a38709fcf2d1974a4", "generation_seconds_batch": 19.27987823006697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6056556701660156, "target_z": 4.468750003697125, "ce": 6.300607204437256, "genuineness": 4.331617832183838, "identity": 0.3471781611442566, "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_Contentment/9f510dbdcf5a5ccc5229ca8d0c1a65cd6e452c619a7a010ef2c7e3bae2142d3b.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "a01ea7c9d960f0cf668478b908fea66cf1660fe69b12574cae0be86bac025a3b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ef8edb03bd41d74a5030aebe1b9efd70e4dbcbd713b1d2c3a5d8da320b343d97", "generation_seconds_batch": 19.73517887108028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.275031089782715, "target_z": 3.8125001996447683, "ce": 6.316492557525635, "genuineness": 4.174716949462891, "identity": 0.5171750783920288, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/a01ea7c9d960f0cf668478b908fea66cf1660fe69b12574cae0be86bac025a3b.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "a05945ef5928b91049c59d429dafb49ba54b369e60dc9529cebee2593a646ef7", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f6e31cd5666a21aca2678192d58733cfb24195b94f547c4cbc621ef68acb8234", "generation_seconds_batch": 20.911702485987917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9050462245941162, "target_z": 3.078124990757187, "ce": 6.213237762451172, "genuineness": 4.6956281661987305, "identity": 0.7961755990982056, "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_Contentment/a05945ef5928b91049c59d429dafb49ba54b369e60dc9529cebee2593a646ef7.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "a0766e5c74a40f9488a2a7249ed2e2977fdda2d562c962f85b54c62879427d41", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "661492602c1a52670b9ed2026e92b22be2cdccdd0e22ec41ea6b063eb47de5eb", "generation_seconds_batch": 20.58589483401738, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.574167490005493, "target_z": 4.406249774475354, "ce": 6.181467056274414, "genuineness": 4.18726921081543, "identity": 0.4184362590312958, "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_Contentment/a0766e5c74a40f9488a2a7249ed2e2977fdda2d562c962f85b54c62879427d41.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "a0be0d0cca88b21fea7e43c10cb9dbe748aace687bee00fb26ae0ad68134da53", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "74d8cf34c46b432beedadfc02f1990ec67e2bce84f6449aee1be803339c97355", "generation_seconds_batch": 14.298114493954927, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.56654953956604, "target_z": 2.406250011091376, "ce": 6.133810997009277, "genuineness": 4.419482707977295, "identity": 0.621150016784668, "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_Contentment/a0be0d0cca88b21fea7e43c10cb9dbe748aace687bee00fb26ae0ad68134da53.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "a0e93f9b440066813c33b31f73ae3205029786917f3236ca89c10d5e6cd72897", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "82741f0b938d3711b72886f40542689e52cc7cda8924fe3533416d49a8958c35", "generation_seconds_batch": 14.547752770013176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8895561695098877, "target_z": 1.0625000517597547, "ce": 6.181467056274414, "genuineness": 4.369274139404297, "identity": 0.535426914691925, "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_Contentment/a0e93f9b440066813c33b31f73ae3205029786917f3236ca89c10d5e6cd72897.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": "a1a0355704675c4009adb7b807f80c25907a3b9564da76c8bf406e7fb44f7155", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "a8963199b0819f04b75650983e76256e9ce2dd5e4799d40a9ffc073d306f7e19", "generation_seconds_batch": 15.139024809002876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.912918210029602, "target_z": 3.0937499297546185, "ce": 6.23706579208374, "genuineness": 4.281409740447998, "identity": 0.6956108212471008, "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_Contentment/a1a0355704675c4009adb7b807f80c25907a3b9564da76c8bf406e7fb44f7155.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": "a1b263aee5cc5704ceb2c2fcf61a8b234ab3f44b88b8e179bacb043ef12015bc", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Someone moved the little blue chair.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cac6edd6d32ff1448ec6852483ce78fce811d6f1c726d2aab8781e8728a5aa8e", "generation_seconds_batch": 19.481856803991832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.54267954826355, "target_z": 4.343750018485626, "ce": 6.38797664642334, "genuineness": 4.268857479095459, "identity": 0.11930731683969498, "hypothesis": "Someone moved the little blue chair. It used to stand here beside the tall bookshelf. We can put it back after lunch.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/a1b263aee5cc5704ceb2c2fcf61a8b234ab3f44b88b8e179bacb043ef12015bc.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": "a1c0440b2d2820e089c6c5026634ad43c14a75ac6a3bb6e6f4f2ca6899717b49", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "10c56d704167cc72ecce5f0e99bf59cf67b36afe07648ec9b706a3f5e5756486", "generation_seconds_batch": 19.586984080960974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4639594554901123, "target_z": 4.187500155279264, "ce": 6.403861999511719, "genuineness": 4.20609712600708, "identity": 0.5783281326293945, "hypothesis": "Die Schlösser 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_Contentment/a1c0440b2d2820e089c6c5026634ad43c14a75ac6a3bb6e6f4f2ca6899717b49.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "a28e435d7db0d4d2a979ccff5f4109e7259c64e034ddab496d10f9f868274e7f", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bd64021d2696248549c8fed282e1ebea2b337acda8e461ffe5bb7535a0c2aa6d", "generation_seconds_batch": 19.43443990999367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5584235191345215, "target_z": 4.374999896480491, "ce": 5.736677646636963, "genuineness": 3.9927117824554443, "identity": 0.5675634145736694, "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_Contentment/a28e435d7db0d4d2a979ccff5f4109e7259c64e034ddab496d10f9f868274e7f.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "a308b0abaadf279035ff84685d7f601d85f8d3962fb7b801a854863581b2952f", "bucket": "emo_Contentment", "phase": "wording", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f1639ffa89ad7d568ade65f9f7ac0dd8fea36f0ef043c6462750e7232131a7c2", "generation_seconds_batch": 17.539729319047183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.078230619430542, "target_z": 3.421875068396819, "ce": 6.229123115539551, "genuineness": 4.406930446624756, "identity": 0.7133162617683411, "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_Contentment/a308b0abaadf279035ff84685d7f601d85f8d3962fb7b801a854863581b2952f.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "a30f40c54cf51f79cefbffaa1c4bc6ace8ef2f5364e45c2901470a43a87d3264", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e509e92762ed7127a52122ff2bb25333c53809ef1c020f71b02a2537504dd86a", "generation_seconds_batch": 19.90394168207422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5584235191345215, "target_z": 4.374999896480491, "ce": 5.935244083404541, "genuineness": 4.105680465698242, "identity": 0.7218493223190308, "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_Contentment/a30f40c54cf51f79cefbffaa1c4bc6ace8ef2f5364e45c2901470a43a87d3264.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "a37de3ee71824be5454dfddb8d2cd9643c2ab1b7b4ee1b597da3e36e7cd36859", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "22b95bf87924760aeacdf0cb4db10ce17d822e89e085ad0f857cbb72d0e86369", "generation_seconds_batch": 19.63312729401514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4954473972320557, "target_z": 4.249999911268992, "ce": 6.09409761428833, "genuineness": 4.337893962860107, "identity": 0.7799135446548462, "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_Contentment/a37de3ee71824be5454dfddb8d2cd9643c2ab1b7b4ee1b597da3e36e7cd36859.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "a38499f929cad0037ecb55493c33f3cfaa0b244abd1ae21ddb201b81823810b0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "96c4940650ed72d43c9fa7a36298173cb266f5c9ac7be6345bd3ce7c1f98478c", "generation_seconds_batch": 19.521187103004195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1333346366882324, "target_z": 3.531249877994864, "ce": 6.23706579208374, "genuineness": 4.6203155517578125, "identity": 0.5728756189346313, "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_Contentment/a38499f929cad0037ecb55493c33f3cfaa0b244abd1ae21ddb201b81823810b0.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "a3c05a4a4a19b5deeb4ae33e2fc1bd46061e3804902d5cd0534b8ec242ff2e67", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "1305cc3feaeb27651079514cb85e9efbfafe898bf847eed78d6b9a06c1d2eb0a", "generation_seconds_batch": 22.576964769978076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8656861782073975, "target_z": 3.0000000591540052, "ce": 6.149696350097656, "genuineness": 4.2751336097717285, "identity": 0.6022725105285645, "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_Contentment/a3c05a4a4a19b5deeb4ae33e2fc1bd46061e3804902d5cd0534b8ec242ff2e67.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "a3c4abe77b3cc7fb5102236bc07db2203a14974dbb95be7cb87e7c4445c7a7b3", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "de607a4d98519c4c5de67a4a70e1f1dbd4b523da859772c5496d4c270e3e0a19", "generation_seconds_batch": 20.746104321908206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6528878211975098, "target_z": 4.56250011091376, "ce": 6.427689552307129, "genuineness": 4.168440818786621, "identity": 0.43315982818603516, "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_Contentment/a3c4abe77b3cc7fb5102236bc07db2203a14974dbb95be7cb87e7c4445c7a7b3.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "a3f4ae39264cc5f51e725fa59d3f2e970b4e8e47fa540dee8bb95e6e8f476676", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f6eb08d492b17f54b2a8fe99ccfed84e65e5db892c969a0aa0655ded96d537f7", "generation_seconds_batch": 20.060054392088205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6686317920684814, "target_z": 4.593749988908624, "ce": 6.197352409362793, "genuineness": 4.300237655639648, "identity": 0.7936936616897583, "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_Contentment/a3f4ae39264cc5f51e725fa59d3f2e970b4e8e47fa540dee8bb95e6e8f476676.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "a47a1dc0ffe0887e756a7a5b219a7a49d1b3452af0ef3c4043377ea985ff44e9", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "1b3c28429962df052fd4b74ffbbbe7d3915115ad35b0683602f4fdfc7be586a1", "generation_seconds_batch": 19.394681360921822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2907750606536865, "target_z": 3.843750077639632, "ce": 6.181467056274414, "genuineness": 4.193545341491699, "identity": 0.2127465158700943, "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_Contentment/a47a1dc0ffe0887e756a7a5b219a7a49d1b3452af0ef3c4043377ea985ff44e9.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "a4da4a51a637909fb2b8a196ab960bdff76697f95017cd6017734decba898b86", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "4d42861289b21e831922f5667e550633bbc0238958dbaf0424239f43ace1f4ef", "generation_seconds_batch": 19.570843569003046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7318618297576904, "target_z": 2.7343749131175543, "ce": 6.1894097328186035, "genuineness": 4.519899368286133, "identity": 0.483926922082901, "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_Contentment/a4da4a51a637909fb2b8a196ab960bdff76697f95017cd6017734decba898b86.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "a53c20b5ab8c1c5b815f78569c7344ec19d67a7613a661a407a020136b070fed", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d36811b641bc64d4ca72c144324ab7f6ec83a0c913c896ffaac4f88a1e47bf42", "generation_seconds_batch": 14.8290553529514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4639594554901123, "target_z": 4.187500155279264, "ce": 6.252951145172119, "genuineness": 4.557555198669434, "identity": 0.7513281106948853, "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_Contentment/a53c20b5ab8c1c5b815f78569c7344ec19d67a7613a661a407a020136b070fed.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "a547fb7514e275ec7c677c8f3bbf6e97c666f17076d994fe84ddcfd7066d43b7", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "03d0bd04e01600f87bcef5bafb2651c4d322eb1853779f97e926b9bb07a4341c", "generation_seconds_batch": 14.441985199926421, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.526935577392578, "target_z": 4.312500140490763, "ce": 6.133810997009277, "genuineness": 4.300237655639648, "identity": 0.6948027610778809, "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_Contentment/a547fb7514e275ec7c677c8f3bbf6e97c666f17076d994fe84ddcfd7066d43b7.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "a5928568b9e57bc0af21d6fb0aa7ed9b83b0929ee52000a51f4bc846a33d094c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "9f93fb6aca54f50a3705eee396c92dc88e84e0e1648d4c7c4c18e9cad2d6a42e", "generation_seconds_batch": 19.923084749956615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.030998468399048, "target_z": 3.3281249611801837, "ce": 6.252951145172119, "genuineness": 4.381826400756836, "identity": 0.56467604637146, "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_Contentment/a5928568b9e57bc0af21d6fb0aa7ed9b83b0929ee52000a51f4bc846a33d094c.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "a5e53abf57cc5779c730974f34a634bf819c70f3243b8c65f118610cae9e7788", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ca13b2fc091f42436c7590214706edbf503e8ef5fa94be3b4aecc82d367c048c", "generation_seconds_batch": 20.604053384042345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9328522682189941, "target_z": 1.1484375711696628, "ce": 6.117925643920898, "genuineness": 4.3504462242126465, "identity": 0.5678476095199585, "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_Contentment/a5e53abf57cc5779c730974f34a634bf819c70f3243b8c65f118610cae9e7788.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "a62a147d331427d0f124d61b689aa0be550c00d84c954265c62a25d0cbb07192", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "dae575b3e3260d651408c4321cbcda6b2ddc2b2295c6a2c19f0c6ebeafcb4ae8", "generation_seconds_batch": 19.060159850982018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9837663173675537, "target_z": 3.234374853963549, "ce": 5.990842819213867, "genuineness": 4.256305694580078, "identity": 0.6121661067008972, "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_Contentment/a62a147d331427d0f124d61b689aa0be550c00d84c954265c62a25d0cbb07192.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "a661fe14cccc7d846489e31525d93f74f70e78b9708918bec858b51ca4210757", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8bd6ff059adb7905b30386c4a25e75eccd0a6aa564ea123d825c5a67a4a4165e", "generation_seconds_batch": 14.713354922016151, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1333346366882324, "target_z": 3.531249877994864, "ce": 6.2767791748046875, "genuineness": 4.111956596374512, "identity": 0.6120899319648743, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/a661fe14cccc7d846489e31525d93f74f70e78b9708918bec858b51ca4210757.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": "a6665dec7abbefd97db5596290d399e86ad4f7239659be272f33b8168481648f", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "57ea7d5cfb4d1cf9d8580417951b4b5c0ecc74fd46a27d2c6211f383b1d4980f", "generation_seconds_batch": 14.608003514935263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9758943319320679, "target_z": 3.2187499149661174, "ce": 6.221180438995361, "genuineness": 4.174716949462891, "identity": 0.4989217519760132, "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_Contentment/a6665dec7abbefd97db5596290d399e86ad4f7239659be272f33b8168481648f.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "a6aed5278283b4004f5b696c77c46a0ca72f8b146a3e861035e667558cc814f7", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "5c8783c49fe37d474c2f423a82640362de246c254148e4e81fec6d6526f91fd9", "generation_seconds_batch": 21.384794921032153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.574167490005493, "target_z": 4.406249774475354, "ce": 6.300607204437256, "genuineness": 4.557555198669434, "identity": 0.48585355281829834, "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_Contentment/a6aed5278283b4004f5b696c77c46a0ca72f8b146a3e861035e667558cc814f7.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "a6d8b4d247f134067cda290fec5198bd16ad11c3c08a2189aaa1ebbfbec22f7c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "08baaa40226cf66a2fc624c4cd69b81e75e0d6773160798fdc02aeb8713c893b", "generation_seconds_batch": 21.70743421895895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1805667877197266, "target_z": 3.6249999852114985, "ce": 6.308549880981445, "genuineness": 4.18726921081543, "identity": 0.5208137035369873, "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_Contentment/a6d8b4d247f134067cda290fec5198bd16ad11c3c08a2189aaa1ebbfbec22f7c.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "a70ddd4d7688ec4a52774b81d70ca30ed3d40c2b51139454c80fe78256ba25dd", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "497d52ab1078da025cc325801082d60cc152562550a497060d5be24dc394a892", "generation_seconds_batch": 19.27682355605066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0703585147857666, "target_z": 3.4062498927833653, "ce": 6.2767791748046875, "genuineness": 3.8546390533447266, "identity": 0.5553985238075256, "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_Contentment/a70ddd4d7688ec4a52774b81d70ca30ed3d40c2b51139454c80fe78256ba25dd.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "a725106858aab72bb0bc5d0e1b4d6bc7a0445f6f7c231b6459e6241fcdf667b7", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a5a2441a2058fc036d0e22d4bd7602a56abb99a0786b9f951ad79fd6b95812f3", "generation_seconds_batch": 23.453917777049355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.275031089782715, "target_z": 3.8125001996447683, "ce": 5.903473377227783, "genuineness": 4.13078498840332, "identity": 0.5413373112678528, "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_Contentment/a725106858aab72bb0bc5d0e1b4d6bc7a0445f6f7c231b6459e6241fcdf667b7.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": "a7396dbfb6ab6e7bccaaa0c0867721b1107c6a3ccf88984b92a9e31f6ed10568", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5f9226ea849fdb8d2b7b92ece54ced75a1f5dd4fb5498bf18a239b6feb91c978", "generation_seconds_batch": 19.586984080960974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.259286880493164, "target_z": 3.781249848417861, "ce": 6.332377910614014, "genuineness": 4.3504462242126465, "identity": 0.5197114944458008, "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_Contentment/a7396dbfb6ab6e7bccaaa0c0867721b1107c6a3ccf88984b92a9e31f6ed10568.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "a73c86b5383cf0c9d4fb458fb3aff981a903ff5625dc4e8dc954dc462c7dff9a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "809fa02619a14660b4efed300a83794d624573576cec2344cb3999b7f43cd50f", "generation_seconds_batch": 19.55234413407743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4482152462005615, "target_z": 4.156249804052357, "ce": 6.229123115539551, "genuineness": 4.118232727050781, "identity": 0.2778036296367645, "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_Contentment/a73c86b5383cf0c9d4fb458fb3aff981a903ff5625dc4e8dc954dc462c7dff9a.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "a8087648f396da88b369b49e0d7c92abf27d8ee1f97c1decda9f2d08a0d2b76e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "0e68a512651f3e6e88cd9337f35826c63b63cc50086e666dd131378a2eb934f5", "generation_seconds_batch": 19.590318121016026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4405972957611084, "target_z": 2.156250040668379, "ce": 6.181467056274414, "genuineness": 4.457139015197754, "identity": 0.48501521348953247, "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_Contentment/a8087648f396da88b369b49e0d7c92abf27d8ee1f97c1decda9f2d08a0d2b76e.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "a83c69208e5ae4b5825165def473afca0ae05f431d3578e6074f1e1eea75da95", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a5f4d5dfe9085586538ff8fde96b34aaab766382ca8b1a8ce21c762720a00bef", "generation_seconds_batch": 22.881160077056848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.416727304458618, "target_z": 4.093750048062629, "ce": 6.213237762451172, "genuineness": 4.337893962860107, "identity": 0.6689021587371826, "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_Contentment/a83c69208e5ae4b5825165def473afca0ae05f431d3578e6074f1e1eea75da95.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": "a8437d79927e58293a5bf6a98a358565618f224a847cfb20655b14e987b9acf6", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I wrote the number on the envelope.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a35b1a43fca25c9f3db267b86fce47874aabc7f31ea0d8e92c9543464e72b77a", "generation_seconds_batch": 14.600105297053233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.298647165298462, "target_z": 3.8593752532530856, "ce": 6.443574905395508, "genuineness": 4.337893962860107, "identity": 0.253286749124527, "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_Contentment/a8437d79927e58293a5bf6a98a358565618f224a847cfb20655b14e987b9acf6.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "a87549e3e8bc9bb8265eb5d44c11b498f960b2acbff927448108e1554c99dd85", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "48017a1b64f50c94e986bafd9543948f8c50fdfc03d2bf4479c5197994e8e903", "generation_seconds_batch": 20.61819623201154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.306519031524658, "target_z": 3.874999955634496, "ce": 6.395919322967529, "genuineness": 3.8546390533447266, "identity": 0.3863416910171509, "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_Contentment/a87549e3e8bc9bb8265eb5d44c11b498f960b2acbff927448108e1554c99dd85.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "c7c039fdbeb010e9efda4c2063c7801ef47a567baa35d0c50851b6bb35d6ff54", "generation_seconds_batch": 14.30846586509142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.51144540309906, "target_z": 2.2968749648773095, "ce": 6.054384231567383, "genuineness": 4.250029563903809, "identity": 0.6180506944656372, "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_Contentment/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "a8cb7daa94f5e9247de0ec7961149c082bbf1b40c651ff4f4b235eb01411d3d2", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "61f0ca60aa0846436e2fdde2b10a78b3fd0da2fc3749aebe0ea6e6429101d910", "generation_seconds_batch": 20.98695431498345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.306519031524658, "target_z": 3.874999955634496, "ce": 6.2767791748046875, "genuineness": 3.860914945602417, "identity": 0.36434733867645264, "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_Contentment/a8cb7daa94f5e9247de0ec7961149c082bbf1b40c651ff4f4b235eb01411d3d2.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "a8f4b336e5f942f72a8f1ee82f5ce4df1f0b7daf14834511eee3247f0e78c25c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "127986616bfcb7a72800578ec9f9ab73876477300ca32187c22d8f934d9054b6", "generation_seconds_batch": 14.400635089026764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6213996410369873, "target_z": 4.4999998816919895, "ce": 6.356205940246582, "genuineness": 4.425758361816406, "identity": 0.3905009627342224, "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_Contentment/a8f4b336e5f942f72a8f1ee82f5ce4df1f0b7daf14834511eee3247f0e78c25c.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "a90a31b78229dc8f039fe25505ef771479faf9e52c63f3b2bf423d69d78890a6", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a5281549d9e0b2de0312bd535f73bd175ae16acee0f259ac9225b55fbc8ba9fc", "generation_seconds_batch": 14.832112937001511, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1963107585906982, "target_z": 3.6562498632063622, "ce": 6.41180419921875, "genuineness": 4.055472373962402, "identity": 0.5762657523155212, "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_Contentment/a90a31b78229dc8f039fe25505ef771479faf9e52c63f3b2bf423d69d78890a6.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "a926d1eeee03c84f3c83add308421a3f04d954e3d9fe6a3bad9ddfd8536d8b85", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "33e45c5fbe0c6a28714dec45c3dc335a0c12ed85a585810fbbf069a8ddddba80", "generation_seconds_batch": 21.34214420907665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.684375762939453, "target_z": 4.6249998669034875, "ce": 6.3641486167907715, "genuineness": 4.193545341491699, "identity": 0.43875330686569214, "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_Contentment/a926d1eeee03c84f3c83add308421a3f04d954e3d9fe6a3bad9ddfd8536d8b85.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "a92e470c85383742be20c8197eb976f55a21fb8abcf9760a8495303176c112e1", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ea1942fe3a5c1a435d0070ef546d45b74456e289fbe1da6bc521020cba3f931e", "generation_seconds_batch": 19.772828968940303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.526935577392578, "target_z": 4.312500140490763, "ce": 6.252951145172119, "genuineness": 4.055472373962402, "identity": 0.28550565242767334, "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_Contentment/a92e470c85383742be20c8197eb976f55a21fb8abcf9760a8495303176c112e1.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "79aa6566372199675db270afd55eb8e0577e0ce13026233a0bc4f24d3295e782", "generation_seconds_batch": 14.583863836945966, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9601503610610962, "target_z": 3.1875000369712536, "ce": 6.149696350097656, "genuineness": 4.268857479095459, "identity": 0.7061229944229126, "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_Contentment/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "a95c9570216a9b249875923a927e26e18c3057b97c293e2decbb955c862d6716", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "7a5395e35a2f26d16d9851d9a744e57189758e43dab253cd3aca62349a246a86", "generation_seconds_batch": 19.58510578190908, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1097185611724854, "target_z": 3.4843748243865464, "ce": 6.149696350097656, "genuineness": 4.331617832183838, "identity": 0.7459498643875122, "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_Contentment/a95c9570216a9b249875923a927e26e18c3057b97c293e2decbb955c862d6716.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "a9ba4f5c19b70db2385b179b63604fa8dd9e9452559abb2a1e71c0ef9df79e8c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "98c8d4a53da8746f5a13ec90e8dff764051b466cdd1cf7c78bf086a395b87584", "generation_seconds_batch": 17.139457298908383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.747351884841919, "target_z": 4.749999852114986, "ce": 5.967014789581299, "genuineness": 4.168440818786621, "identity": 0.627831757068634, "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_Contentment/a9ba4f5c19b70db2385b179b63604fa8dd9e9452559abb2a1e71c0ef9df79e8c.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "aa1cbf961c8abe496a461b51c7fb506fe60b9a32147006342499630a77dfeaf4", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e57edb8ff7fa78c46f53504eedf3380504579fe4ce2a9ed0618ee63bdfc37021", "generation_seconds_batch": 19.436959319049492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9837663173675537, "target_z": 3.234374853963549, "ce": 6.308549880981445, "genuineness": 4.457139015197754, "identity": 0.672671377658844, "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_Contentment/aa1cbf961c8abe496a461b51c7fb506fe60b9a32147006342499630a77dfeaf4.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "aa7224388eb1afe7842b6c1564c5411686b68de524c3767a9e22df79d80ddb5e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "931e2d467db8577db56f1c4e1aa78b2ed19f3798f141be81c3d9d732d31ab8b7", "generation_seconds_batch": 19.250395511975512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.598037600517273, "target_z": 2.4687500036971253, "ce": 6.165581703186035, "genuineness": 4.482243061065674, "identity": 0.5667116641998291, "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_Contentment/aa7224388eb1afe7842b6c1564c5411686b68de524c3767a9e22df79d80ddb5e.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "aaa2c4e9af29ab902af72c089035db9d6b70742a1e0506cd356988bedfac17c1", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bb2fe880cdb4b8e6dad108315d7a4f486d8f081dbc3f4ca7a6d91a056f11d464", "generation_seconds_batch": 19.59923379297834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7790939807891846, "target_z": 2.8281250203341894, "ce": 6.141753673553467, "genuineness": 4.3127899169921875, "identity": 0.5732777714729309, "hypothesis": "ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/aaa2c4e9af29ab902af72c089035db9d6b70742a1e0506cd356988bedfac17c1.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": "ab64adc0a728b315a1d02bb600844790501b11ac18aff139f5ead23fef3ba73e", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f80b15fd5adb7eb42fc9f0ee3d7607de03f00c0312558e716a6300453a926902", "generation_seconds_batch": 14.429919424001127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.030998468399048, "target_z": 3.3281249611801837, "ce": 6.229123115539551, "genuineness": 4.519899368286133, "identity": 0.6928421854972839, "hypothesis": "De weg gaat linksaf na de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/ab64adc0a728b315a1d02bb600844790501b11ac18aff139f5ead23fef3ba73e.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "664735ae8669058bfa39ce9570111443816268fbc202ca33c2f7b0051c590cad", "generation_seconds_batch": 14.510139674996026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4091092348098755, "target_z": 2.0937500480626294, "ce": 6.3641486167907715, "genuineness": 3.9676074981689453, "identity": 0.23607131838798523, "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_Contentment/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "ab7e2415b331b248fff807b0dc7596b456296582d26ddd22282cdc66232cf59b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "7d3445baf02f2e4915ded14d2f1b195322ff625cf8b24f2c54ff0b50e9c057c0", "generation_seconds_batch": 23.089647065033205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9286623001098633, "target_z": 3.125000044365504, "ce": 6.24500846862793, "genuineness": 4.231201171875, "identity": 0.6634038686752319, "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_Contentment/ab7e2415b331b248fff807b0dc7596b456296582d26ddd22282cdc66232cf59b.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "ac50686b15f6a07460890162fa38dfb3443e5c08e283299b8999ec09f95c5c1d", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f9c5db557f4d7adeb0b1ca7701daa684bf3a59e364dc24d00df62e20664e4662", "generation_seconds_batch": 20.908456837991253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4482152462005615, "target_z": 4.156249804052357, "ce": 6.24500846862793, "genuineness": 4.432034492492676, "identity": 0.5021382570266724, "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_Contentment/ac50686b15f6a07460890162fa38dfb3443e5c08e283299b8999ec09f95c5c1d.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "ace94fc388b709558815540117e79d6b7b16b45363800a23392286ef34d4081c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "794619b1ab043704a149f77b6e14b3971c41b45af44d59e61dee0582bd85b0de", "generation_seconds_batch": 19.57667818502523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2277989387512207, "target_z": 3.7187500924281336, "ce": 6.09409761428833, "genuineness": 4.3127899169921875, "identity": 0.7519513368606567, "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_Contentment/ace94fc388b709558815540117e79d6b7b16b45363800a23392286ef34d4081c.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "acf914a36804539cfb0d191ffb0a4104c56139e8093c1361ae16f1df9555c4d3", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "4b77d57a170dfa5619e4836317ae7592d125661ae3bf13e19c011a1517f4b51e", "generation_seconds_batch": 23.994906384963542, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1333346366882324, "target_z": 3.531249877994864, "ce": 6.475345611572266, "genuineness": 4.344170093536377, "identity": 0.5077627301216125, "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_Contentment/acf914a36804539cfb0d191ffb0a4104c56139e8093c1361ae16f1df9555c4d3.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "ad01c2ed19c1b571b2abdc589699eea1e24b6668d883c2a6e951b986eeb8fb6f", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "0f40f4ba589cbbeb5558ba6671092dbf13089eada70f30876429ba3c78c59432", "generation_seconds_batch": 15.228429208043963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.015254497528076, "target_z": 3.29687508318532, "ce": 6.141753673553467, "genuineness": 4.444586753845215, "identity": 0.4760449230670929, "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_Contentment/ad01c2ed19c1b571b2abdc589699eea1e24b6668d883c2a6e951b986eeb8fb6f.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "ad88226ff448511d0da9cde200158797d5c47627285bd963718d61f00ad32f92", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c23da6f29914eed5a4a9f444fd91c526eaf3c49320c646ae7db4b4bd99dcd6e4", "generation_seconds_batch": 20.32179498008918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6056556701660156, "target_z": 4.468750003697125, "ce": 6.125868320465088, "genuineness": 4.281409740447998, "identity": 0.18766124546527863, "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_Contentment/ad88226ff448511d0da9cde200158797d5c47627285bd963718d61f00ad32f92.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3b468a353ca972c95e047ac6b7e45dffcec75aa19c208fc3fa786c2f12bded1f", "generation_seconds_batch": 14.331369496067055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8105820417404175, "target_z": 2.890625012939939, "ce": 6.149696350097656, "genuineness": 4.344170093536377, "identity": 0.765254020690918, "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_Contentment/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "adfba0bdaaea748c2399b445af2b540afe2478a44c914c200654d07c53ea1509", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "8b64b34010a26befee6cf2056b18ca6c0d8568c93d048a5ab1e19daeb3d576bc", "generation_seconds_batch": 15.202359320945106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0939745903015137, "target_z": 3.4531249463916827, "ce": 6.372091293334961, "genuineness": 3.911123275756836, "identity": 0.730897843837738, "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_Contentment/adfba0bdaaea748c2399b445af2b540afe2478a44c914c200654d07c53ea1509.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "10c000e08614b6176b27d5529b8f5fc33291ec521f882407d501a321f174e115", "generation_seconds_batch": 14.459670276963152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8814301490783691, "target_z": 3.031249937148869, "ce": 6.395919322967529, "genuineness": 3.9927117824554443, "identity": 0.2563830018043518, "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_Contentment/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "ae346c81d38a7783eb3a0742aaff30c38ee72ee1627238b4f5185c5cef855ff9", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "27aa0a40cac2c0103e34be6f9721b5ec4a3b1f8f78e5601c18d674efaed65d79", "generation_seconds_batch": 19.512215920025483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4639594554901123, "target_z": 4.187500155279264, "ce": 6.070269584655762, "genuineness": 4.557555198669434, "identity": 0.7599607706069946, "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_Contentment/ae346c81d38a7783eb3a0742aaff30c38ee72ee1627238b4f5185c5cef855ff9.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": "ae5f5332686e252f6853b65f567e108ab07ac794ba4ec6d7c6ad31246f85b055", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cab7ac125acca3fca84790ed98ca4a87bb5e7106f1397f5f1670ed28b2588a59", "generation_seconds_batch": 14.398584791924804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3537511825561523, "target_z": 3.968750062851131, "ce": 6.260893821716309, "genuineness": 4.256305694580078, "identity": 0.5859261751174927, "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_Contentment/ae5f5332686e252f6853b65f567e108ab07ac794ba4ec6d7c6ad31246f85b055.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "aebd37909c57d939e8c61700089760d32e29579e97f3c90f6f71fa4f19dcba44", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d26ec494a8d88ccab10a4fc2c06667c20e8b8c020b8cf55c89465d91dd099edd", "generation_seconds_batch": 21.132584615028463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.306519031524658, "target_z": 3.874999955634496, "ce": 6.292664527893066, "genuineness": 4.457139015197754, "identity": 0.5800272226333618, "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_Contentment/aebd37909c57d939e8c61700089760d32e29579e97f3c90f6f71fa4f19dcba44.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "af234a4e8b3eb783b51dd6d2eb4815e2f6f65b75c6d9210921ca943adf4f4eee", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e192b0fd2d0876c40d8871e09bd65aa1626741706559306508e991d5224de5a2", "generation_seconds_batch": 14.990697697037831, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.479703426361084, "target_z": 4.218750033274128, "ce": 6.284721851348877, "genuineness": 4.086852550506592, "identity": 0.22395670413970947, "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_Contentment/af234a4e8b3eb783b51dd6d2eb4815e2f6f65b75c6d9210921ca943adf4f4eee.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "af716fa3f689bf2fc9a31e8cb70639774feba034ace8eb5b2ccf6af4db7a4ebd", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b25196b8ff2b0053cdf40ae54648339bcf0f705218640d168292e996442dcea1", "generation_seconds_batch": 21.2841795590939, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2989009618759155, "target_z": 1.8749999556344958, "ce": 6.149696350097656, "genuineness": 4.15588903427124, "identity": 0.3759937286376953, "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_Contentment/af716fa3f689bf2fc9a31e8cb70639774feba034ace8eb5b2ccf6af4db7a4ebd.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "af93b5e34966ba43ccb3f04aa05fb38260ec59614bf992a64cffd125d19f98a7", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f15ec2bb59e7970e909b71e63d2cf42c71ff203181009475da9a841fe166eee9", "generation_seconds_batch": 20.896110223955475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.43247127532959, "target_z": 4.124999926057493, "ce": 5.919358730316162, "genuineness": 3.9676074981689453, "identity": 0.4815904498100281, "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_Contentment/af93b5e34966ba43ccb3f04aa05fb38260ec59614bf992a64cffd125d19f98a7.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "afb32a609d01a8fdd275fbc037905ea7e5b99dd3925267ee0baca4b25b007ae1", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "915543b6cbc4930129f0db282a317457906014c5d5106a861a124fc0aa6cf826", "generation_seconds_batch": 22.223138472996652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0467424392700195, "target_z": 3.3593748391750475, "ce": 6.181467056274414, "genuineness": 4.268857479095459, "identity": 0.5685666799545288, "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_Contentment/afb32a609d01a8fdd275fbc037905ea7e5b99dd3925267ee0baca4b25b007ae1.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": "afb768e6f259cc4653fb12822d0957f081c35076662c95482c08f9d899ae59c7", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b621a3e5ec1758c9231fe2270d4230873ae1a6498bfa7c4b6aa785edb4d1e2da", "generation_seconds_batch": 19.289344487013295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.700119733810425, "target_z": 4.656249744898352, "ce": 6.006728172302246, "genuineness": 4.18099308013916, "identity": 0.720319390296936, "hypothesis": "Las llaves están en la mesa de la cocina, miren el cajón y luego junto a la ventana, llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/afb768e6f259cc4653fb12822d0957f081c35076662c95482c08f9d899ae59c7.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "afd7ba19e0ec8aa6d61c0edf8f8f161fb8b6eb3dfd1b7eb661a241c335d08e58", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e0dd3bcfcfb58da425b6d67975b15816a6e8dc5ddd1f76cec8229d37085416f3", "generation_seconds_batch": 20.17170429509133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2277989387512207, "target_z": 3.7187500924281336, "ce": 6.268836498260498, "genuineness": 4.005263805389404, "identity": 0.4453141689300537, "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_Contentment/afd7ba19e0ec8aa6d61c0edf8f8f161fb8b6eb3dfd1b7eb661a241c335d08e58.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": "b03678dc0298d4f9bf12aac69faf36b5815032a9f7d67e08579006a86e5f5696", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ead721ffd28c5f476a97650c987e0dc040b3c3363a2f523a1725efea889c335a", "generation_seconds_batch": 19.28625742800068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.43247127532959, "target_z": 4.124999926057493, "ce": 6.205295085906982, "genuineness": 4.256305694580078, "identity": 0.3401329517364502, "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_Contentment/b03678dc0298d4f9bf12aac69faf36b5815032a9f7d67e08579006a86e5f5696.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "b0c42291cc41b9328d0c546eed8e6eddb288aeaced51d6ec3b5ff370591aa86e", "bucket": "emo_Contentment", "phase": "wording", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "460764be790d6503db62c5bfbb3d0cc3a43bc2e61113d56d95696a5ee79bef1c", "generation_seconds_batch": 18.151324541890062, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0861027240753174, "target_z": 3.4375002440102724, "ce": 6.316492557525635, "genuineness": 4.218649387359619, "identity": 0.50382000207901, "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_Contentment/b0c42291cc41b9328d0c546eed8e6eddb288aeaced51d6ec3b5ff370591aa86e.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "b133c24b1c13ad9cedcaf6eb33cd16a8828564c8a5a77538f5de0cc0a795cda6", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "bf757e580d23913f2b7a2803263c1db0c8f74669d74b11ad4d4ed6fe53df5eb1", "generation_seconds_batch": 20.562167907948606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6610137224197388, "target_z": 2.593749988908624, "ce": 6.324435234069824, "genuineness": 4.532451152801514, "identity": 0.5778956413269043, "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_Contentment/b133c24b1c13ad9cedcaf6eb33cd16a8828564c8a5a77538f5de0cc0a795cda6.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "b1bff5ee0323b281377f0937404f3c3b44576f0488907f4c5c584e6f8fa8f058", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "318aea97ec7459b0fb13aff0edb4a213953a19eec77fce88597feeaad78d3da7", "generation_seconds_batch": 19.900769473053515, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.416727304458618, "target_z": 4.093750048062629, "ce": 6.260893821716309, "genuineness": 4.394378662109375, "identity": 0.7288771867752075, "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_Contentment/b1bff5ee0323b281377f0937404f3c3b44576f0488907f4c5c584e6f8fa8f058.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "b1e4a9eb450d5cb25b6185ce35afa3fff1ea93ae6feb978f94387872825f90eb", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "0f16b1d1c41c68d1a45ac88aaca5fe39679c2b12ca8e516f8ba4953b46bd3aa4", "generation_seconds_batch": 22.613303494057618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.526935577392578, "target_z": 4.312500140490763, "ce": 6.268836498260498, "genuineness": 4.469690799713135, "identity": 0.5807284712791443, "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_Contentment/b1e4a9eb450d5cb25b6185ce35afa3fff1ea93ae6feb978f94387872825f90eb.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "b2ba177780009e52e5b3ad310b8394db7bf77258121bb43a661d0bc64367c023", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "0b00c2a48f728ccfdc4c76a8814e9a5952037869b28a4c1e7b3f73ffd2530bd9", "generation_seconds_batch": 21.735164173995145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5508054494857788, "target_z": 2.3749998964804906, "ce": 6.046441555023193, "genuineness": 4.218649387359619, "identity": 0.561623215675354, "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_Contentment/b2ba177780009e52e5b3ad310b8394db7bf77258121bb43a661d0bc64367c023.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "b3633690233de14cbba30e54234ec08d1ed8a5d805139b6cc6e0dc282e38693c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "517edac31fdaf3d554bf0b7f82fb8c13f9dbd769ced6e47da274942725a3863c", "generation_seconds_batch": 22.00115426001139, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4639594554901123, "target_z": 4.187500155279264, "ce": 6.395919322967529, "genuineness": 4.557555198669434, "identity": 0.5951193571090698, "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_Contentment/b3633690233de14cbba30e54234ec08d1ed8a5d805139b6cc6e0dc282e38693c.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "b3b6ae82fc0d03f12510c2aeb2d8db421256484673260e06aad1eb6e39fe9668", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "69a4a3201aa20782462675434be7add3229895d533f65bf8ece35f5d9555b2e9", "generation_seconds_batch": 17.385060355998576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.747351884841919, "target_z": 4.749999852114986, "ce": 6.133810997009277, "genuineness": 4.174716949462891, "identity": 0.6744463443756104, "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_Contentment/b3b6ae82fc0d03f12510c2aeb2d8db421256484673260e06aad1eb6e39fe9668.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "b3db40a6b59036bc57397dd1eaf7a0795b04b5c384125f3bbf9205f7bd7b0fee", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "affe4600eb344fa32319cf1c2e42d74d7e37e3d60b05fc963334c203b8b3cfe1", "generation_seconds_batch": 20.06162208004389, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4009833335876465, "target_z": 4.062500170067765, "ce": 6.284721851348877, "genuineness": 3.835810661315918, "identity": 0.3365961015224457, "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_Contentment/b3db40a6b59036bc57397dd1eaf7a0795b04b5c384125f3bbf9205f7bd7b0fee.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "69fe95dc11e035167e76e78b6244f3c7eb45c8f12eaec1c8f314677fce4d20a3", "generation_seconds_batch": 16.557714855996892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2277989387512207, "target_z": 3.7187500924281336, "ce": 6.427689552307129, "genuineness": 4.293961524963379, "identity": 0.5336278080940247, "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_Contentment/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "b463c3026317c9011e98f51bc7abe7d612c254d4de08bba1d77b6322da4dd6d5", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "842d653e6dd51b93420fb6e4342ed82afcc56afee8febbe7756b20a5a634eec0", "generation_seconds_batch": 22.514221188030206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.589911699295044, "target_z": 4.437500125702262, "ce": 6.2767791748046875, "genuineness": 4.243753433227539, "identity": 0.7131228446960449, "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_Contentment/b463c3026317c9011e98f51bc7abe7d612c254d4de08bba1d77b6322da4dd6d5.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "b47082f40d513ffb5d7dbd92267940b90dd4523c6ae36c8516eafdd56f47e908", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "94880e45a4b6cd8d99b6c7f87ac772242965f7214914805f80a8c22b0288351e", "generation_seconds_batch": 19.952623106073588, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6137815713882446, "target_z": 2.499999881691989, "ce": 6.23706579208374, "genuineness": 4.2374773025512695, "identity": 0.375309020280838, "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_Contentment/b47082f40d513ffb5d7dbd92267940b90dd4523c6ae36c8516eafdd56f47e908.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "b4c8d1d869fa3cb3e8afcc60c53145c5059da30efb0abe3b2ff8d9fbd93c5c5f", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "c1bc95f31cdef633cf8534b418bc13e6627a5f13fcebaac31b46ed983c7a710c", "generation_seconds_batch": 14.527432237984613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.574167490005493, "target_z": 4.406249774475354, "ce": 6.125868320465088, "genuineness": 4.469690799713135, "identity": 0.5642530918121338, "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_Contentment/b4c8d1d869fa3cb3e8afcc60c53145c5059da30efb0abe3b2ff8d9fbd93c5c5f.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "b4f9268a63840a5ad895eeb32c356f298722cf4239a2353f8352826f02740b30", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "0d0251228780fb42cae04bd87717d9dd3f339d532052b783782d4ba0e4c67a1b", "generation_seconds_batch": 19.60497835604474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.43247127532959, "target_z": 4.124999926057493, "ce": 6.181467056274414, "genuineness": 4.570107460021973, "identity": 0.845180094242096, "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_Contentment/b4f9268a63840a5ad895eeb32c356f298722cf4239a2353f8352826f02740b30.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": "b5f73975c64da4e5a37b3d0f89c6745b87a6fc96c7d9ae17b86445cb6649536d", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cec1f1b5ca64be0f35ca0de6e2511bfbdf1e4b98201d824435a9a140e423ec9f", "generation_seconds_batch": 14.535463180975057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.32226300239563, "target_z": 3.9062498336293596, "ce": 6.348263263702393, "genuineness": 4.143336772918701, "identity": 0.5322660207748413, "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_Contentment/b5f73975c64da4e5a37b3d0f89c6745b87a6fc96c7d9ae17b86445cb6649536d.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "b61e553e88748096cc7371daef760f97b7ce98eec8b87693734df2ce46244842", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "df3c72d4cdd5591222736fb46209d3ade4cf27fa4594f861aa8a70d395486abf", "generation_seconds_batch": 19.512215920025483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4639594554901123, "target_z": 4.187500155279264, "ce": 6.260893821716309, "genuineness": 4.444586753845215, "identity": 0.6592332124710083, "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_Contentment/b61e553e88748096cc7371daef760f97b7ce98eec8b87693734df2ce46244842.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": "b674c3518a75baf88d9c67323f25486df2d1bf276778ee1ad0a13b531e38b732", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b241a334437ddb103deb793b9591222e4a1bffdf052d15ba82eacdd648a2bdd6", "generation_seconds_batch": 14.664150257012807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.574167490005493, "target_z": 4.406249774475354, "ce": 6.316492557525635, "genuineness": 4.406930446624756, "identity": 0.7717214822769165, "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_Contentment/b674c3518a75baf88d9c67323f25486df2d1bf276778ee1ad0a13b531e38b732.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "b6a634b24dd850f80543aedbead20966ca4e98a598accb13203386cd6a349559", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b96c79938b57eac3bd790afa0b7d694cd697621dc9dce3dd6cfb954b8682a8d1", "generation_seconds_batch": 24.439234171062708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5111913681030273, "target_z": 4.281249789263856, "ce": 6.213237762451172, "genuineness": 4.306513786315918, "identity": 0.596067488193512, "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_Contentment/b6a634b24dd850f80543aedbead20966ca4e98a598accb13203386cd6a349559.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "b6ddc7dd646a818e34657caba1a62ee520fd8f3b78c94e55f31f2d55567a44fc", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "64aa4d62dce4b34d90fe22ccc170006ea5a0f3d8343f374a67002b24d5391d17", "generation_seconds_batch": 21.953701136983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.125462770462036, "target_z": 3.5156251756134536, "ce": 6.205295085906982, "genuineness": 3.9299514293670654, "identity": 0.22536584734916687, "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_Contentment/b6ddc7dd646a818e34657caba1a62ee520fd8f3b78c94e55f31f2d55567a44fc.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "b6ec1500b18ae1ade30f2adc656cd721c9b6a3d62d319ccd0a2f029a202867bd", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9f27a6ad396b50b413330199953fe9db755107f97906df518b17c154799190d4", "generation_seconds_batch": 16.43085816502571, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4482152462005615, "target_z": 4.156249804052357, "ce": 5.919358730316162, "genuineness": 4.055472373962402, "identity": 0.41435641050338745, "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_Contentment/b6ec1500b18ae1ade30f2adc656cd721c9b6a3d62d319ccd0a2f029a202867bd.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "b702ac06ff1e1a0c93e81d82e5bdaddab416d5164f2b9e7ce37225634e0688bc", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "89aab28f10ba0e3ff8df24666cb807f8fcec7983fff6e64a0beae17615943146", "generation_seconds_batch": 19.56050372205209, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.54267954826355, "target_z": 4.343750018485626, "ce": 6.41180419921875, "genuineness": 4.319066047668457, "identity": 0.30865174531936646, "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_Contentment/b702ac06ff1e1a0c93e81d82e5bdaddab416d5164f2b9e7ce37225634e0688bc.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "b76a5c7f87997982629cb54bf5d4185f0631f8d1e145b49b902378ecc1d0c109", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d00e2c886faaa6621c33fd6d16c12a7ab3ad0e69d51c8dca2d2f5282c88b0e5f", "generation_seconds_batch": 14.832112937001511, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2435429096221924, "target_z": 3.7499999704229974, "ce": 6.475345611572266, "genuineness": 4.18099308013916, "identity": 0.4992810785770416, "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_Contentment/b76a5c7f87997982629cb54bf5d4185f0631f8d1e145b49b902378ecc1d0c109.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "b7a6ac44441d7a7bdb3331545a5800a275e63e0985187b15f343fc0991a5a845", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "12c3c96ae85b9471f276b04f433080f53a12b8e6c7e08c036d85f6fb34b2d563", "generation_seconds_batch": 19.938610797049478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5584235191345215, "target_z": 4.374999896480491, "ce": 6.221180438995361, "genuineness": 4.482243061065674, "identity": 0.7596375942230225, "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_Contentment/b7a6ac44441d7a7bdb3331545a5800a275e63e0985187b15f343fc0991a5a845.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "b7b809594c5a88abdb872fa3be058cffd5138bfe150b693894a2e445be6c9e2e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2716526d82b011fe91a3d8530d9d45b61970090bfe832f9f6148fdf43a476344", "generation_seconds_batch": 16.403993866057135, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.684375762939453, "target_z": 4.6249998669034875, "ce": 6.38003396987915, "genuineness": 4.193545341491699, "identity": 0.31778484582901, "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_Contentment/b7b809594c5a88abdb872fa3be058cffd5138bfe150b693894a2e445be6c9e2e.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "b7e9bedfef2840653fb332bacba2111875f8fc53763477333e2d241249865e81", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9137be53c57bac457672b3db6ab9c639be97a1f28e34b982ebbb10cff417f1cf", "generation_seconds_batch": 19.914938758010976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.589911699295044, "target_z": 4.437500125702262, "ce": 6.348263263702393, "genuineness": 4.111956596374512, "identity": 0.3858693540096283, "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_Contentment/b7e9bedfef2840653fb332bacba2111875f8fc53763477333e2d241249865e81.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "b8130fa6b740dc6b4c63259bb9e45572fb27dc2814a14f3b90c13f65edb54f3f", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e079a64afe56b3d87cb6d98fb96e71a39a1011f21b24caa47a1b3d7a67dd9bd4", "generation_seconds_batch": 20.394868689007126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5923875570297241, "target_z": 0.4726562976004888, "ce": 5.974957466125488, "genuineness": 4.086852550506592, "identity": 0.6065242290496826, "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_Contentment/b8130fa6b740dc6b4c63259bb9e45572fb27dc2814a14f3b90c13f65edb54f3f.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "b9009bc560f57cb6b9e4d41bd6a19cb0e09a969bf5ec8e6c54c021fd5d7a53fb", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "8b4f0e468911ddc712323f7ccf037224e822ef66053dfd8ddff6fd6d7f113dac", "generation_seconds_batch": 14.647038997034542, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.637143611907959, "target_z": 4.531249759686853, "ce": 6.443574905395508, "genuineness": 4.381826400756836, "identity": 0.254097580909729, "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_Contentment/b9009bc560f57cb6b9e4d41bd6a19cb0e09a969bf5ec8e6c54c021fd5d7a53fb.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": "b9026e02a25cb4fb8199621cf39a9d857cf6c7677b1363ca77cb1d841a0a6064", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "07d4baa0104599af02c45d03df592c2ec80b21b2b091cef9d01701010e1b82b8", "generation_seconds_batch": 14.445381347090006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6213996410369873, "target_z": 4.4999998816919895, "ce": 6.2767791748046875, "genuineness": 4.457139015197754, "identity": 0.5476596355438232, "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_Contentment/b9026e02a25cb4fb8199621cf39a9d857cf6c7677b1363ca77cb1d841a0a6064.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "b9350b0e93f584b5f1d4ab50e53eccb232def04490c45c977c6c5b8e6b5ef672", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "9314286acef859cadb0fd86a2b4eb1883242f527637bdc45790b27f8a8af0bf0", "generation_seconds_batch": 20.911702485987917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.030998468399048, "target_z": 3.3281249611801837, "ce": 6.125868320465088, "genuineness": 4.193545341491699, "identity": 0.7231833934783936, "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_Contentment/b9350b0e93f584b5f1d4ab50e53eccb232def04490c45c977c6c5b8e6b5ef672.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "b998124abea775ae847f5c2477a3178c79730c102b881450c10fe5eee7549174", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f949e7241d04cfa53eccf2fbe211525ddde3e18f889fb8d45ca1b673a0d93f9c", "generation_seconds_batch": 21.133779039955698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7633498907089233, "target_z": 2.7968749057233038, "ce": 6.117925643920898, "genuineness": 4.362998008728027, "identity": 0.4654890298843384, "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_Contentment/b998124abea775ae847f5c2477a3178c79730c102b881450c10fe5eee7549174.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "b99bbf8c1b49b32a3ecfb9f12905a3321851993fe0d50c357907e22b07d708d9", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b458e737fc9e66c96e1a6bd8467abb0061735382942be1f28d05285ed327b7e1", "generation_seconds_batch": 19.987298988969997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.834197998046875, "target_z": 2.9374998299322344, "ce": 6.006728172302246, "genuineness": 4.20609712600708, "identity": 0.5994884371757507, "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_Contentment/b99bbf8c1b49b32a3ecfb9f12905a3321851993fe0d50c357907e22b07d708d9.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "b9a39946be4658b1cd25eb64fd1a29460b293adb9eaab01b2360ce6f1ea7d391", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f25c493a5b357633d14b732a8b69958a51f82ed53631bfbdb79f807c6ceafb5a", "generation_seconds_batch": 19.537826783023775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7158639430999756, "target_z": 4.687500096125259, "ce": 6.157639026641846, "genuineness": 4.2751336097717285, "identity": 0.5784502029418945, "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_Contentment/b9a39946be4658b1cd25eb64fd1a29460b293adb9eaab01b2360ce6f1ea7d391.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "b9e25891ac88d4237470ac9ae4b9cd743daecc9ebbcbd0149dea8bb80b5e33c6", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f2788e4f078727e8ba29acee29e6646f106b8e705fa2b9a7d49113c867c3019b", "generation_seconds_batch": 15.857073536957614, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1963107585906982, "target_z": 3.6562498632063622, "ce": 6.300607204437256, "genuineness": 4.482243061065674, "identity": 0.6797935962677002, "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_Contentment/b9e25891ac88d4237470ac9ae4b9cd743daecc9ebbcbd0149dea8bb80b5e33c6.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "ba2b412a80659d80c302f18a2aa7aead234ea53a383c6316993025fc671a55f0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "bf458515ac25a1bc8bfb75b7f0e373c4daebefc1a3baf6416593089da6b02477", "generation_seconds_batch": 14.94908744795248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.212054967880249, "target_z": 3.68750021443327, "ce": 6.23706579208374, "genuineness": 4.256305694580078, "identity": 0.43706831336021423, "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_Contentment/ba2b412a80659d80c302f18a2aa7aead234ea53a383c6316993025fc671a55f0.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "ba4e9893deb040823d53b975d5cc0e99af4cfe77886afb2de6d942c6aad030c5", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f954f2b9a5490a0fb546ad5b393c79c4fa797e590049d736e0b01d2926aa2348", "generation_seconds_batch": 14.520092447986826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1333346366882324, "target_z": 3.531249877994864, "ce": 6.403861999511719, "genuineness": 4.218649387359619, "identity": 0.5784593820571899, "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_Contentment/ba4e9893deb040823d53b975d5cc0e99af4cfe77886afb2de6d942c6aad030c5.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "7837056139fd0c451e21a1f405c1826901331c0a807fa2ea63f3478c5483cb92", "generation_seconds_batch": 14.811049113050103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.235671043395996, "target_z": 3.734375268041587, "ce": 6.229123115539551, "genuineness": 4.425758361816406, "identity": 0.6056540608406067, "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_Contentment/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "bab55e2cb5911342d18bf351b76e3c4997e723b80ba943063cb486bb1f35718e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b536664cbb43cae8bba4d26a74d2b64875eeab23602c55237df6ff0dbd04356e", "generation_seconds_batch": 22.588254391099326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7158639430999756, "target_z": 4.687500096125259, "ce": 6.078212261199951, "genuineness": 4.268857479095459, "identity": 0.7672938108444214, "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_Contentment/bab55e2cb5911342d18bf351b76e3c4997e723b80ba943063cb486bb1f35718e.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "bae74456f8314b5325e2ab8325a42e2a77442229570f9d64c4b0e0560a763e57", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "74e86054ba56a03c42161ab4d78937e133d2b7642440e1a0ac80cc8cada0314a", "generation_seconds_batch": 21.980817293049768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2277989387512207, "target_z": 3.7187500924281336, "ce": 6.292664527893066, "genuineness": 4.086852550506592, "identity": 0.28217247128486633, "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_Contentment/bae74456f8314b5325e2ab8325a42e2a77442229570f9d64c4b0e0560a763e57.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "bbf0b01d475dbe399274bfa506a69bc05338e73da76fd64e2c1535a7b7a9f415", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d68efdc039ba4b6e2a410aabe67c71778d286287af4f823213e65a34336cda4d", "generation_seconds_batch": 19.250395511975512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1532686948776245, "target_z": 1.5859375194099081, "ce": 6.300607204437256, "genuineness": 4.319066047668457, "identity": 0.48839664459228516, "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_Contentment/bbf0b01d475dbe399274bfa506a69bc05338e73da76fd64e2c1535a7b7a9f415.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "bc3b84592e6c43b177ebf17683e7df148fabdc35a0eabaf4607ed759db03cc7e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "841be927bd5ef9c48d566b7b91210191d5842cccf208a1e7476a3e4a82b41314", "generation_seconds_batch": 14.408623041003011, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8260719776153564, "target_z": 4.906249715321349, "ce": 6.054384231567383, "genuineness": 3.886019229888916, "identity": 0.37687113881111145, "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_Contentment/bc3b84592e6c43b177ebf17683e7df148fabdc35a0eabaf4607ed759db03cc7e.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "be006163cd0a0fef1aff8b87378b2ccfb12bae16d26c5436c8fec9f6c49ad097", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "cda9585f16d916930adee662b799a75a99ae86bc5ade48e152e780f8f035cf79", "generation_seconds_batch": 20.931699516950175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2277989387512207, "target_z": 3.7187500924281336, "ce": 6.213237762451172, "genuineness": 4.406930446624756, "identity": 0.48608893156051636, "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_Contentment/be006163cd0a0fef1aff8b87378b2ccfb12bae16d26c5436c8fec9f6c49ad097.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "be0092800119c21162c6f44bb06d1a0592cb46e5165bfbebc0e6cf64cd362298", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "1e5eef115bf96bbacd74848fa15ba96c95091298fac34b3476b82439c0153fb1", "generation_seconds_batch": 21.2841795590939, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1572047472000122, "target_z": 1.593750107216635, "ce": 6.070269584655762, "genuineness": 4.444586753845215, "identity": 0.7241970896720886, "hypothesis": "De door 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_Contentment/be0092800119c21162c6f44bb06d1a0592cb46e5165bfbebc0e6cf64cd362298.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "be4960cfd9652a63abbb8b56ea33f95d10345fd704592ca6c17ddff222ed8669", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e2e37fdb0aa995556874b00222b46e014ace707d67aea35860facfac1c5e64ff", "generation_seconds_batch": 19.58508861507289, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1097185611724854, "target_z": 3.4843748243865464, "ce": 6.300607204437256, "genuineness": 4.218649387359619, "identity": 0.5892187356948853, "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_Contentment/be4960cfd9652a63abbb8b56ea33f95d10345fd704592ca6c17ddff222ed8669.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "bed0f5edcfb0156e7a49455a291ab68be3c46bd17338231ebc238f0cd558740e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "139c2fb7ef0a02330c7751f8b290d0d27ffd4aad45e738b33b4e4b718ab2e6e9", "generation_seconds_batch": 19.619587383931503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1963107585906982, "target_z": 3.6562498632063622, "ce": 6.165581703186035, "genuineness": 4.457139015197754, "identity": 0.4251236617565155, "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_Contentment/bed0f5edcfb0156e7a49455a291ab68be3c46bd17338231ebc238f0cd558740e.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "c08dbcab5c8f1687eb834bca8b5001a2cfffd1a7cc2ef118a03048cbafb19d6a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "9f7f549176a5f5388f069616c2374c058aeab04b8d7d4afb9e46e7bfb1800dae", "generation_seconds_batch": 20.452680178917944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.345879077911377, "target_z": 3.953124887237677, "ce": 6.181467056274414, "genuineness": 4.3504462242126465, "identity": 0.7515721321105957, "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_Contentment/c08dbcab5c8f1687eb834bca8b5001a2cfffd1a7cc2ef118a03048cbafb19d6a.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "c11c47434453900d0355b9b07f078affcf19098d4eb334434e283a37f7be1342", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "bfd35bcba74b4616b4d694482ea138ea53bd20b95e6461b37eef58d8742bf4bd", "generation_seconds_batch": 19.201237648027018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2041828632354736, "target_z": 3.6718750388198163, "ce": 5.919358730316162, "genuineness": 4.143336772918701, "identity": 0.4776984453201294, "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_Contentment/c11c47434453900d0355b9b07f078affcf19098d4eb334434e283a37f7be1342.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "c1746b10b8a84f87adbe199307416165467c5a195a705b5bcae2182d51567d16", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "9be8662608654a80a1d58f899eee16a95259778292a47ad7cf529952f755511a", "generation_seconds_batch": 20.03565426694695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.259286880493164, "target_z": 3.781249848417861, "ce": 6.221180438995361, "genuineness": 4.469690799713135, "identity": 0.7973460555076599, "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_Contentment/c1746b10b8a84f87adbe199307416165467c5a195a705b5bcae2182d51567d16.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "c174dd461fb828d5627b8d74361b71695501b5f7502cb5bc1602d5e34f35bc66", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "b5c824002a17685f6e2c78b306c3a5844d7ddf4d5a17ba96b2dd2a1a51138b40", "generation_seconds_batch": 21.82350979500916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.747351884841919, "target_z": 4.749999852114986, "ce": 6.324435234069824, "genuineness": 4.6956281661987305, "identity": 0.7220243811607361, "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_Contentment/c174dd461fb828d5627b8d74361b71695501b5f7502cb5bc1602d5e34f35bc66.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "c1d36746a18ef801dce02c03320ee127bc069fb9b5d8b609df8c1c7030c6c48c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "67d8f621946d9cd4d01a2152963344fe4ab36886429a3355c649e9753b7eb265", "generation_seconds_batch": 20.01667128293775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4954473972320557, "target_z": 4.249999911268992, "ce": 6.173524379730225, "genuineness": 4.406930446624756, "identity": 0.7534167766571045, "hypothesis": "V'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/c1d36746a18ef801dce02c03320ee127bc069fb9b5d8b609df8c1c7030c6c48c.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "c214efbb06f8c73d0da443392a17d26aedec84c560a9f904f4e1c11cf6ffdbb5", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2c7628b3406155db88e38011e2d7383088c95b2928ce64010b45e04fc7e7cc9c", "generation_seconds_batch": 21.70743421895895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1333346366882324, "target_z": 3.531249877994864, "ce": 6.483288764953613, "genuineness": 4.369274139404297, "identity": 0.5414252877235413, "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_Contentment/c214efbb06f8c73d0da443392a17d26aedec84c560a9f904f4e1c11cf6ffdbb5.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "c21a2e381b67d343bd82bab1c9e45ea406dc2bf55574ed4674fe465e675b12db", "bucket": "emo_Contentment", "phase": "wording", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "232fc850a9ebb58cc554e5ee47055939a7662a75100c64fb174affc9b5a60fc3", "generation_seconds_batch": 15.634526391979307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0231266021728516, "target_z": 3.312500258798774, "ce": 6.252951145172119, "genuineness": 4.557555198669434, "identity": 0.7435885071754456, "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_Contentment/c21a2e381b67d343bd82bab1c9e45ea406dc2bf55574ed4674fe465e675b12db.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "c230cc14acf6de796872ec80e6467243363ca49282bca3a5a534f96e2efe7159", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0de6b0f92d1f2080a63e427cc3335ef9400dcb9de0122e84ae170e588edfac80", "generation_seconds_batch": 14.871062690974213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0624866485595703, "target_z": 3.390625190401955, "ce": 6.022613525390625, "genuineness": 4.168440818786621, "identity": 0.6546692848205566, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/c230cc14acf6de796872ec80e6467243363ca49282bca3a5a534f96e2efe7159.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "c29ebffb477864242127e4f5b77085b49e7e00d55204a825522c520db7a22ddb", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "6663a384f2697c73ea337876b02d4f73b31e8a6944bbd8a7f93851ff01c4b306", "generation_seconds_batch": 20.498778149019927, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.235671043395996, "target_z": 3.734375268041587, "ce": 5.911416053771973, "genuineness": 4.519899368286133, "identity": 0.7644538879394531, "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_Contentment/c29ebffb477864242127e4f5b77085b49e7e00d55204a825522c520db7a22ddb.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "c31c00c0200abf159ae9a84bbe8d3439a090d7c567ff7b941efae10c1927228f", "bucket": "emo_Contentment", "phase": "wording", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "bbc188a86ef86cbe57555bacebfaeeab3edb5d73fc145795ec2b444903e2cb8a", "generation_seconds_batch": 17.539729319047183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.542933464050293, "target_z": 2.3593749574830585, "ce": 6.038498878479004, "genuineness": 4.356721878051758, "identity": 0.6472815871238708, "hypothesis": "Ik heb het kleine doosel geventerd. 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_Contentment/c31c00c0200abf159ae9a84bbe8d3439a090d7c567ff7b941efae10c1927228f.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": "c37777f73f0486bbba1cd4b059ae35e9484f3f4068f7711130c8cbc194108c74", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "68343061698a237c51c36a78d3c60b499ccac856e038b21f0ab5854c09008ee7", "generation_seconds_batch": 19.34451213805005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8890483379364014, "target_z": 5.031250173764891, "ce": 6.157639026641846, "genuineness": 4.306513786315918, "identity": 0.5359656810760498, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí junto a la estantería. La colocaremos después de comer.", "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_Contentment/c37777f73f0486bbba1cd4b059ae35e9484f3f4068f7711130c8cbc194108c74.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "c37e5f23294e65e2524a12dd0ce78cbf9a05ba4f695961cd47363635bc48d09a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "414cc2274fa070e22d12d85e50a0235798f964a9bba8d3d91ce731aa0246482f", "generation_seconds_batch": 19.825778675964102, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7316079139709473, "target_z": 4.718749974120122, "ce": 6.038498878479004, "genuineness": 4.2751336097717285, "identity": 0.5095443725585938, "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_Contentment/c37e5f23294e65e2524a12dd0ce78cbf9a05ba4f695961cd47363635bc48d09a.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "bc7712b96b27c2a889124f47ad9f3f5f569ca30eafdc60d37f547f006d7501ec", "generation_seconds_batch": 14.422055994044058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7869659662246704, "target_z": 2.843749959331621, "ce": 6.260893821716309, "genuineness": 4.645420074462891, "identity": 0.7937197685241699, "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_Contentment/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "c3bf1edf050bd561e32c17065ff23b4928e0330292c4852d62cdc2e6619432b7", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "9e6c1f27198d10f96b9d90a476d13e22d078ee0a7a0ba7c62a39044425d53f3d", "generation_seconds_batch": 22.7584306220524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.794584035873413, "target_z": 4.843749959331621, "ce": 6.1894097328186035, "genuineness": 4.3504462242126465, "identity": 0.747407078742981, "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_Contentment/c3bf1edf050bd561e32c17065ff23b4928e0330292c4852d62cdc2e6619432b7.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": "c3f4ce4aa85fd938d873c6c5601fea2611c302c3965087052d65f4fc0c32ae5b", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The keys are on the kitchen table.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "67e10e2d09e1035d4a78e6416a2e08252197fef9eb8f38f37225049122a62b5f", "generation_seconds_batch": 19.161463001044467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6213996410369873, "target_z": 4.4999998816919895, "ce": 6.324435234069824, "genuineness": 3.9801597595214844, "identity": 0.14898397028446198, "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_Contentment/c3f4ce4aa85fd938d873c6c5601fea2611c302c3965087052d65f4fc0c32ae5b.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "c40acd9e0cddeb92bb0e1d7f5666a0aae89b3b49e192280180a6ec1c8f6044e3", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "6934f4365ff9f7ebadb724a92af170733752ccfaa83749542d68e36fc651265c", "generation_seconds_batch": 20.500792959937826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0703585147857666, "target_z": 3.4062498927833653, "ce": 6.133810997009277, "genuineness": 4.444586753845215, "identity": 0.7229580879211426, "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_Contentment/c40acd9e0cddeb92bb0e1d7f5666a0aae89b3b49e192280180a6ec1c8f6044e3.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "c480bd461f6457c4d4e97e5002aefca58ded110dc89eb57385dbfc8264ffd87c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "86996119bf053848f9cf5ed33f4e14634a867f046290e96dc41a8005ed4e8108", "generation_seconds_batch": 20.75561525905505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.526935577392578, "target_z": 4.312500140490763, "ce": 6.324435234069824, "genuineness": 4.231201171875, "identity": 0.24278324842453003, "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_Contentment/c480bd461f6457c4d4e97e5002aefca58ded110dc89eb57385dbfc8264ffd87c.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "4172892ee6d5d9d1aef211d5965706ae60296fbf8558b84ad7625f6bb1042b0c", "generation_seconds_batch": 14.355021241935901, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8971742391586304, "target_z": 3.0625000517597547, "ce": 6.2767791748046875, "genuineness": 4.394378662109375, "identity": 0.7017050981521606, "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_Contentment/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.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": "c4eb3f2da3259d065516fa1c3d036afd329d60721706b86322269424b07ae951", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The road turns left behind the bridge.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e4374f436c033481acecc27d911ea01cbb8c3c05be7af3716d773b576859e347", "generation_seconds_batch": 19.348003874067217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.298647165298462, "target_z": 3.8593752532530856, "ce": 6.38003396987915, "genuineness": 4.049196243286133, "identity": 0.16852042078971863, "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_Contentment/c4eb3f2da3259d065516fa1c3d036afd329d60721706b86322269424b07ae951.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "c4ed9cf49f56edbeae413a79d7851e9ddaef205247cdedc4121228e4d529a407", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "11f69fa78e30b7344a76a79e01466f001447b77922117745e2ec8524b18c96b9", "generation_seconds_batch": 19.87429629196413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.54267954826355, "target_z": 4.343750018485626, "ce": 6.2767791748046875, "genuineness": 4.231201171875, "identity": 0.6429663896560669, "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_Contentment/c4ed9cf49f56edbeae413a79d7851e9ddaef205247cdedc4121228e4d529a407.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": "c51cff38d24e089cea3875b6a02ef3c2034e7a8ed40be84bf69382ed1c1d6449", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1a377857ad5a1a8a65ed848c09971bb49ba8664ebe925ec579c9dfea8ce56b81", "generation_seconds_batch": 19.263845068984665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1097185611724854, "target_z": 3.4843748243865464, "ce": 6.2767791748046875, "genuineness": 4.124508857727051, "identity": 0.7374746799468994, "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_Contentment/c51cff38d24e089cea3875b6a02ef3c2034e7a8ed40be84bf69382ed1c1d6449.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "c5a181aeec7181f5d00a9ba862cd64a2253ecafa2c5ad35834a238b5404d8671", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "53f56aef4ca53677b91f3cf983383872899c1286bea4b9bcd9e9008bc54a6841", "generation_seconds_batch": 21.562214985024184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1963107585906982, "target_z": 3.6562498632063622, "ce": 6.459460258483887, "genuineness": 4.256305694580078, "identity": 0.5533106327056885, "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_Contentment/c5a181aeec7181f5d00a9ba862cd64a2253ecafa2c5ad35834a238b5404d8671.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "c5ff4eb7edff1ff5e8238c54f465d055af806e5507ad62475411600786456975", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "330964d31c9b5d522c78776e792130fd30e59847d935ada2dc1580bb84d6c2ea", "generation_seconds_batch": 19.608696948038414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4639594554901123, "target_z": 4.187500155279264, "ce": 6.197352409362793, "genuineness": 4.457139015197754, "identity": 0.5646839737892151, "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_Contentment/c5ff4eb7edff1ff5e8238c54f465d055af806e5507ad62475411600786456975.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "c6296ee1335cdd9ebf9cd13041f81b22309feaf52a07609e9c8c001a87db395b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "8ec13fd1b821ace0d0700b35c07879af05cb350e8952ca9998dd75a9b26dffa8", "generation_seconds_batch": 19.233606011024676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8184540271759033, "target_z": 2.9062499519373706, "ce": 6.09409761428833, "genuineness": 4.293961524963379, "identity": 0.26847514510154724, "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_Contentment/c6296ee1335cdd9ebf9cd13041f81b22309feaf52a07609e9c8c001a87db395b.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "c6c54b5bb9cd5c8b5dbc9b86783359dd5a081ef2b41b4fd0f4380e5c08fa20de", "bucket": "emo_Contentment", "phase": "wording", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "fdbf9ab350d450996e7294124187d306bbd7db415c0c3713d968f8f5019c20b2", "generation_seconds_batch": 15.651001809048466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5111913681030273, "target_z": 4.281249789263856, "ce": 6.38003396987915, "genuineness": 4.607763767242432, "identity": 0.3228170871734619, "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_Contentment/c6c54b5bb9cd5c8b5dbc9b86783359dd5a081ef2b41b4fd0f4380e5c08fa20de.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "c728e7e23bfce8c8fb17f9ccf7795f0b288e16e025b419a8499ce9f308b3e403", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "bd29c50300fe707fc5e31a50a33acb36babee30ab47351c35c603ae40fe59a72", "generation_seconds_batch": 19.590318121016026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6730756759643555, "target_z": 0.6328124547102146, "ce": 6.308549880981445, "genuineness": 4.413206577301025, "identity": 0.16983729600906372, "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_Contentment/c728e7e23bfce8c8fb17f9ccf7795f0b288e16e025b419a8499ce9f308b3e403.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "c7628223d1bce42ef73d9cb5e63e1e49d7b5ffa205cf4a94d631792665f989f1", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "829b3650b644dca0ff96e89ed20e888975a5ae7fe8efbad0e03658c78cab09da", "generation_seconds_batch": 24.23914376902394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6056556701660156, "target_z": 4.468750003697125, "ce": 6.324435234069824, "genuineness": 4.193545341491699, "identity": 0.3278122544288635, "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_Contentment/c7628223d1bce42ef73d9cb5e63e1e49d7b5ffa205cf4a94d631792665f989f1.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": "c77a8610c69c8b758b69088b7bd15efe0a29620bf298fe4bd6c0ccd5c2f16f50", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The keys are on the kitchen table.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4f64dd0fd77ae2664e5eb4f7e8b42499d6e06036504596133238171bf2b11bac", "generation_seconds_batch": 19.161463001044467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6213996410369873, "target_z": 4.4999998816919895, "ce": 6.340320587158203, "genuineness": 4.055472373962402, "identity": 0.1937623769044876, "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/c77a8610c69c8b758b69088b7bd15efe0a29620bf298fe4bd6c0ccd5c2f16f50.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "c7bb7b42c28d38db76ca32fe6960f1c6d9fa67f1ded483c233051ce85a4ed46f", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "768717e87d2ab43e29dfe8bd4eb1f091cac25352d2c68094b6a6a3b580bec596", "generation_seconds_batch": 21.384794921032153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6528878211975098, "target_z": 4.56250011091376, "ce": 6.316492557525635, "genuineness": 4.532451152801514, "identity": 0.7652080059051514, "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_Contentment/c7bb7b42c28d38db76ca32fe6960f1c6d9fa67f1ded483c233051ce85a4ed46f.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "c7f9cdf1aa17e6c04e9fc5e6af52687ef5afb6a28256ba26bf50f6b451da902d", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "9659b6184112b6630b639763f757cc582875f5b72da30d381056d32fc34d6e1c", "generation_seconds_batch": 21.980817293049768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3301351070404053, "target_z": 3.921875009242813, "ce": 6.332377910614014, "genuineness": 4.21237325668335, "identity": 0.3593711853027344, "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_Contentment/c7f9cdf1aa17e6c04e9fc5e6af52687ef5afb6a28256ba26bf50f6b451da902d.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "6845f4b7f14c468e4484d05138deb58d0b32170240658d521f08b7a380d01ff7", "generation_seconds_batch": 14.331369496067055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0076364278793335, "target_z": 1.2968750831853202, "ce": 6.268836498260498, "genuineness": 4.356721878051758, "identity": 0.7472884058952332, "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_Contentment/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "c82473241b9989f6b67a2cb26f9737057277bbfb59f98de7ed18dd6f55e917a5", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a93416d8f811b759b5e0351439ed85976c8fc356f8e6b582b152a09845450a9c", "generation_seconds_batch": 20.481964682927355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.149078845977783, "target_z": 3.562500229221771, "ce": 6.459460258483887, "genuineness": 4.243753433227539, "identity": 0.5724777579307556, "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_Contentment/c82473241b9989f6b67a2cb26f9737057277bbfb59f98de7ed18dd6f55e917a5.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "c828bad1790388bc34b7720834f0b617e1f18bbe2d88a798176bed53a1abd3bd", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "0ce98cfb6db3570ff15aaa3a855af25462274a1426fb11913970353c3b791dff", "generation_seconds_batch": 16.395434860954992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1805667877197266, "target_z": 3.6249999852114985, "ce": 6.38797664642334, "genuineness": 4.482243061065674, "identity": 0.5449483394622803, "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_Contentment/c828bad1790388bc34b7720834f0b617e1f18bbe2d88a798176bed53a1abd3bd.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "759f4de6b1581fd910218c50d5d9312dd24cced884f130ec18eda7b008bb3c2a", "generation_seconds_batch": 14.512034207000397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0939745903015137, "target_z": 3.4531249463916827, "ce": 6.372091293334961, "genuineness": 4.281409740447998, "identity": 0.23991705477237701, "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_Contentment/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "c8b478e6f7b29d15b368349da97344c00c119fb34e278c711f90174a987850cc", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "c9da424e79a4aafd32f91c350120a8e1788118735614162a3f31bdf4a2cfc820", "generation_seconds_batch": 19.262782260077074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5584235191345215, "target_z": 4.374999896480491, "ce": 6.125868320465088, "genuineness": 4.331617832183838, "identity": 0.6656774282455444, "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_Contentment/c8b478e6f7b29d15b368349da97344c00c119fb34e278c711f90174a987850cc.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": "c8eb37084d6f20d779f353b12e0e55b0d31ff1cccbd4331e78a4c8e0a68c9d5d", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "05e4ed3b324ee07bcd244e5129a4a4ed080f27a8fa8d3b673f8801d530f56349", "generation_seconds_batch": 14.54414551903028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0703585147857666, "target_z": 3.4062498927833653, "ce": 6.1894097328186035, "genuineness": 3.973883628845215, "identity": 0.5498035550117493, "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_Contentment/c8eb37084d6f20d779f353b12e0e55b0d31ff1cccbd4331e78a4c8e0a68c9d5d.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "c989742e7643d2f25d759eceaf5bbe6fab11e0964c10b8874d0e6d13947c4a5c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "eefa70a1d0f70b5b168872f67619cee54b5fe0a274f762e345e89f2263d17d54", "generation_seconds_batch": 19.87429629196413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.43247127532959, "target_z": 4.124999926057493, "ce": 6.284721851348877, "genuineness": 4.432034492492676, "identity": 0.6778155565261841, "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_Contentment/c989742e7643d2f25d759eceaf5bbe6fab11e0964c10b8874d0e6d13947c4a5c.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "cae9d6c8f22ceb68fba894cee2e4886d224001753038f62b7e75fb01f2286801", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b8bfa89bb3650d067776f7566535729d09d9ee2f557cb956d772c384319a0dd2", "generation_seconds_batch": 16.224442829960026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8184540271759033, "target_z": 2.9062499519373706, "ce": 6.332377910614014, "genuineness": 4.319066047668457, "identity": 0.570559024810791, "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_Contentment/cae9d6c8f22ceb68fba894cee2e4886d224001753038f62b7e75fb01f2286801.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "cb18af44835326b656448f3d46d8313b6a9ee689aeec47e55c55b8269b1f000a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f016313016dc301976865027f0398af8c5d009f1b6090a1238b2c8a840eb118f", "generation_seconds_batch": 16.610794609994628, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.235671043395996, "target_z": 3.734375268041587, "ce": 6.324435234069824, "genuineness": 4.406930446624756, "identity": 0.5916790962219238, "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_Contentment/cb18af44835326b656448f3d46d8313b6a9ee689aeec47e55c55b8269b1f000a.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "cb3164c0e72e369f6566366d3d9651e30e63d4201a2985dbd874c97781f4a24f", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "93a6983f0f48ff9aacc689be9baae39a10a7249fa83cb488b9f2e073d3a9d199", "generation_seconds_batch": 19.521187103004195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.007382392883301, "target_z": 3.2812499075718664, "ce": 6.197352409362793, "genuineness": 4.3127899169921875, "identity": 0.5106227993965149, "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_Contentment/cb3164c0e72e369f6566366d3d9651e30e63d4201a2985dbd874c97781f4a24f.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "cc358a497e7c9bd5198a68d10bc44b29a5257ff78a81ed50552aa30ad293eeaa", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e7cda062c2bf82bd4d6914e6259ac846bb4e9ea6e1891505a3a2c392e5724135", "generation_seconds_batch": 19.83019646606408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7397338151931763, "target_z": 2.7499998521149864, "ce": 6.086154937744141, "genuineness": 4.218649387359619, "identity": 0.7457765936851501, "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_Contentment/cc358a497e7c9bd5198a68d10bc44b29a5257ff78a81ed50552aa30ad293eeaa.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "cd2a924ed56bef7d777cf899ee32d0c1e400cc62a7e3860ee2b7803ca3b14581", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a4392a5ef1458180ac8e8896172592e9a011b7f6ff26565a78184ea30e35972c", "generation_seconds_batch": 20.397297626012005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4482152462005615, "target_z": 4.156249804052357, "ce": 6.205295085906982, "genuineness": 4.375550270080566, "identity": 0.7355176210403442, "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_Contentment/cd2a924ed56bef7d777cf899ee32d0c1e400cc62a7e3860ee2b7803ca3b14581.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "cd59cf901c1fed62623489d453a02ad4aca59dc3b9b56ff22f1b2796530d1590", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ac7b76fb8bc951e9a40ca627a2eaade2b91b6eee7c04a743492603ee78ba4d62", "generation_seconds_batch": 22.640119376941584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2435429096221924, "target_z": 3.7499999704229974, "ce": 6.308549880981445, "genuineness": 4.256305694580078, "identity": 0.20525994896888733, "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_Contentment/cd59cf901c1fed62623489d453a02ad4aca59dc3b9b56ff22f1b2796530d1590.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "cd8a0d19e4cf181ebfefb99873d0c4a2ddded5464f8886f3713c942b5707661e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "0244e75a4e4fa0ffcd69be8e05e4780b93316b0572c3589940a6ee0c4eca193f", "generation_seconds_batch": 19.5383565640077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5584235191345215, "target_z": 4.374999896480491, "ce": 5.974957466125488, "genuineness": 4.055472373962402, "identity": 0.6503110527992249, "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_Contentment/cd8a0d19e4cf181ebfefb99873d0c4a2ddded5464f8886f3713c942b5707661e.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "ce2f9c164fa5fbf763c975a32af14d80b0348bcfd9d76e6e4d5229be9d20c5ec", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "8da4c56e611f77d01fcf266ab02497431eb66f5782c7b493fc45c4ee92af1117", "generation_seconds_batch": 15.832512318040244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4954473972320557, "target_z": 4.249999911268992, "ce": 6.292664527893066, "genuineness": 4.250029563903809, "identity": 0.3372969627380371, "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_Contentment/ce2f9c164fa5fbf763c975a32af14d80b0348bcfd9d76e6e4d5229be9d20c5ec.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "ce7d943deb0b4819a6cab21ca260cf87e48cf63d15e30e35828e82d8214cd855", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2d77ebc1d3458a0521b55f61d2dae70482ca61f553c322cec867fa07a0abbf82", "generation_seconds_batch": 16.43085816502571, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8418161869049072, "target_z": 4.937500066548256, "ce": 6.006728172302246, "genuineness": 3.9550557136535645, "identity": 0.4182621240615845, "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_Contentment/ce7d943deb0b4819a6cab21ca260cf87e48cf63d15e30e35828e82d8214cd855.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "ceb52a7b8749e80899581a18042b57005010304f5dc406ecd0ef3a918634d3f8", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a7899f994cf0aa803c509ba8ce7b25bc775924db991e0f01a14910e29689448a", "generation_seconds_batch": 19.39975019299891, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4954473972320557, "target_z": 4.249999911268992, "ce": 6.268836498260498, "genuineness": 4.494794845581055, "identity": 0.22385069727897644, "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_Contentment/ceb52a7b8749e80899581a18042b57005010304f5dc406ecd0ef3a918634d3f8.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "cf1875272adf6af9aca2fad64bf12b533f303b34ece144d91496d2bacce6782e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "47cf3df37da9a2e362c2b1d908c9f0f950105a0a0ac3f56a938e159fff11c685", "generation_seconds_batch": 23.14302464807406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7316079139709473, "target_z": 4.718749974120122, "ce": 6.4515180587768555, "genuineness": 4.281409740447998, "identity": 0.32711678743362427, "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_Contentment/cf1875272adf6af9aca2fad64bf12b533f303b34ece144d91496d2bacce6782e.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "cf67eb9cedf0761e75b622f302e6f3aad0b02af7f7cdf9e24827f7e444077ef4", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "af9a6b03b7053ece202251d4b7fb866ef3930da371d29f685f9031ed28d9eb27", "generation_seconds_batch": 22.588254391099326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.416727304458618, "target_z": 4.093750048062629, "ce": 6.252951145172119, "genuineness": 4.582659721374512, "identity": 0.849947452545166, "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_Contentment/cf67eb9cedf0761e75b622f302e6f3aad0b02af7f7cdf9e24827f7e444077ef4.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "f876e2e40e0429df70247c0650ba1770c9870f188d8d5e0abb78e94ddde47a82", "generation_seconds_batch": 16.508516159956343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.125462770462036, "target_z": 3.5156251756134536, "ce": 6.41180419921875, "genuineness": 4.3127899169921875, "identity": 0.6705617308616638, "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_Contentment/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "cf97a12a75aea4dea3754bc549af8f81310a3d6aafb196f9a03e4499688f2f28", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "cffaf50900f8a2130101bcc6091b51b32e9e0d095f1f77f8fded27ee394d276b", "generation_seconds_batch": 19.39975019299891, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4639594554901123, "target_z": 4.187500155279264, "ce": 6.403861999511719, "genuineness": 4.432034492492676, "identity": 0.2660873830318451, "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_Contentment/cf97a12a75aea4dea3754bc549af8f81310a3d6aafb196f9a03e4499688f2f28.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "cfb06b6644def030fc858cfabcbe3553a460efa0918529b19d365520d4003c14", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "14e97110116da92bde14104b5192af94d9e75b535c3a3f68cf556fb5b45c8763", "generation_seconds_batch": 14.708721422939561, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.991638422012329, "target_z": 3.2500000295770026, "ce": 5.998785495758057, "genuineness": 3.973883628845215, "identity": 0.6252496242523193, "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_Contentment/cfb06b6644def030fc858cfabcbe3553a460efa0918529b19d365520d4003c14.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "d00f918d6c78203a8da8a54a8b771425be5670f0c3922d3d1c0fcf7ffd9b3ee6", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2718da61bfd7d2c45f427ae7b275b5f53aec44ace269ab28f45e831e40ce9ae5", "generation_seconds_batch": 15.228429208043963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2041828632354736, "target_z": 3.6718750388198163, "ce": 6.372091293334961, "genuineness": 4.482243061065674, "identity": 0.6709463596343994, "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_Contentment/d00f918d6c78203a8da8a54a8b771425be5670f0c3922d3d1c0fcf7ffd9b3ee6.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": "d07d1ec7a1057ed428f39aabf0e173741a54eb75ca21b4687917bfd610fb69a5", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd16091ed73aed9801d7650bc5e0a1d14edb821c14ca22f99f78b3f24c23c81c", "generation_seconds_batch": 19.623654350056313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2907750606536865, "target_z": 3.843750077639632, "ce": 6.197352409362793, "genuineness": 4.18099308013916, "identity": 0.7619934678077698, "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_Contentment/d07d1ec7a1057ed428f39aabf0e173741a54eb75ca21b4687917bfd610fb69a5.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "d0deab70b11afa61cd68e732b8912c4b4d8b224c8cc8c5124588a2b007fd13c3", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "34c3596ddc28421e29f00705aa4025907982816e64417a39e14c45494d01bb46", "generation_seconds_batch": 22.549040294950828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3933651447296143, "target_z": 2.0624999334517438, "ce": 6.173524379730225, "genuineness": 4.362998008728027, "identity": 0.6108226180076599, "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_Contentment/d0deab70b11afa61cd68e732b8912c4b4d8b224c8cc8c5124588a2b007fd13c3.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "83fd69cb0eeb9c97f17335516f246d28798f19e0f2643d722293da038308fc97", "generation_seconds_batch": 14.88742979906965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0388705730438232, "target_z": 3.3437501367936378, "ce": 6.443574905395508, "genuineness": 3.9676074981689453, "identity": 0.5469139814376831, "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_Contentment/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "d1e57fee23db69696fce7b3dc59b1a63be78f5162a2ab1bbde42702bf49d09bc", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "78e491ca8a1616e839db913f088b69b55b559ea50e4a43a537d3cce3f4943cc2", "generation_seconds_batch": 22.875912555959076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2435429096221924, "target_z": 3.7499999704229974, "ce": 6.181467056274414, "genuineness": 4.068024158477783, "identity": 0.47972095012664795, "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_Contentment/d1e57fee23db69696fce7b3dc59b1a63be78f5162a2ab1bbde42702bf49d09bc.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "d21307d72a24fc65028dfc66e8b54cde390468e48c309c06942a8a20cee244a5", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "1e2ca03099e353132db60a4dc0f220289e16d7901c40d25e0b254452f9cfdcf5", "generation_seconds_batch": 19.4656971039949, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2831569910049438, "target_z": 1.843750077639632, "ce": 6.252951145172119, "genuineness": 4.494794845581055, "identity": 0.67156982421875, "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_Contentment/d21307d72a24fc65028dfc66e8b54cde390468e48c309c06942a8a20cee244a5.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "aa1c4db6517077058274d8cdde888879c0dffe884a23f0175eb0bce3395675c1", "generation_seconds_batch": 14.418078035931103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.479703426361084, "target_z": 4.218750033274128, "ce": 6.229123115539551, "genuineness": 4.394378662109375, "identity": 0.6499037742614746, "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_Contentment/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "d2cae6f040a4a8c88a5d07fe886e3b12c8cf7950bc07120235e42f8c8423eaaa", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ee465414f4abbf39967c10228bc00edf4074dacc4b0e2c4bed7e6f55d0e8e5f", "generation_seconds_batch": 14.492652300046757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.700119733810425, "target_z": 4.656249744898352, "ce": 6.006728172302246, "genuineness": 4.545003414154053, "identity": 0.6559134721755981, "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_Contentment/d2cae6f040a4a8c88a5d07fe886e3b12c8cf7950bc07120235e42f8c8423eaaa.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": "d2e2c7bf3f24419d6745662afb539f25ad3669cd48f82474f3fa91bb273896cc", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "73aebe13c6b95228d2d5e0a33bb8d413a8f5fd43a181656a2409a002c1bd7e6c", "generation_seconds_batch": 14.607486602035351, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4009833335876465, "target_z": 4.062500170067765, "ce": 6.38003396987915, "genuineness": 4.093128204345703, "identity": 0.5466758608818054, "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_Contentment/d2e2c7bf3f24419d6745662afb539f25ad3669cd48f82474f3fa91bb273896cc.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "d384d2bc4074b38ad44c21b45f7968480d84eda73faa538422968743f656677a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3a0ed478cd94c45b5bc46f136a819f93a6dc162eb8193c9fcc6186b9e81dabff", "generation_seconds_batch": 21.739701717044227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3301351070404053, "target_z": 3.921875009242813, "ce": 6.252951145172119, "genuineness": 3.8420867919921875, "identity": 0.22141043841838837, "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_Contentment/d384d2bc4074b38ad44c21b45f7968480d84eda73faa538422968743f656677a.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "d3d30cf44cd6c23960875331d86cea1817b0dd68ac567021468eb15c34340135", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "1069575e393e8c48f57ca64bc436d1185d403b82d694387d3f89f3b818b5f536", "generation_seconds_batch": 21.109212653012946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6528878211975098, "target_z": 4.56250011091376, "ce": 6.125868320465088, "genuineness": 4.570107460021973, "identity": 0.7476410269737244, "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_Contentment/d3d30cf44cd6c23960875331d86cea1817b0dd68ac567021468eb15c34340135.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "9fe623213ecf21229b5b0286b0775b67d987e23fec85d491818df08e5f98f90f", "generation_seconds_batch": 14.857523272978142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.944406270980835, "target_z": 3.156249922360368, "ce": 6.054384231567383, "genuineness": 4.482243061065674, "identity": 0.49075210094451904, "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_Contentment/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "d42a2ffe6502761d6b66cbd2490afd23bf690086b6ec257a1803ae96ea84091e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "9f3459b07a9347acd39b181a050da72a32ffd9285f21202857dd56fd1c8048a8", "generation_seconds_batch": 19.994879939011298, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7316079139709473, "target_z": 4.718749974120122, "ce": 6.23706579208374, "genuineness": 4.400654315948486, "identity": 0.6491765379905701, "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_Contentment/d42a2ffe6502761d6b66cbd2490afd23bf690086b6ec257a1803ae96ea84091e.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "d4bfd720aec85d0c637e4afdda83dcc57e8ba2e56df4f8426a09a7d995a557d7", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "dd2a24597ee9414b0f6fde994e754180600c50ce2a8c31877fecd0935d2160cd", "generation_seconds_batch": 22.584256325964816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.282902956008911, "target_z": 3.8281249020261785, "ce": 6.38797664642334, "genuineness": 4.18726921081543, "identity": 0.6738736629486084, "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_Contentment/d4bfd720aec85d0c637e4afdda83dcc57e8ba2e56df4f8426a09a7d995a557d7.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "d50834f7420cbb9c5855327d12a4bac1029fd947cdb80278b8e9b89897eb075e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ab65a3ee9be1ac0e46b7946775d986b48200209da56d4d6eef79ed19194985b4", "generation_seconds_batch": 19.900769473053515, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.188438892364502, "target_z": 3.6406251608249525, "ce": 5.982900142669678, "genuineness": 4.049196243286133, "identity": 0.7621766924858093, "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_Contentment/d50834f7420cbb9c5855327d12a4bac1029fd947cdb80278b8e9b89897eb075e.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "d55bdf939699130cb589009071f39259325c8f4ba8fe75f08e13814e5a14599a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "8c092b5d1b2f74d2c33f11ae06ca2d5ce77a1c096e9944b9b42defa13a61c21e", "generation_seconds_batch": 16.74979054101277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2907750606536865, "target_z": 3.843750077639632, "ce": 5.863759994506836, "genuineness": 4.218649387359619, "identity": 0.6862151026725769, "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_Contentment/d55bdf939699130cb589009071f39259325c8f4ba8fe75f08e13814e5a14599a.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "d5930e1768247a84fe1641bd9f68a36feb0965d791bb3d93145d43ca0baaa202", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "fca616825f41eb844f056112aaa16817e67558b43e99f6ffcb4bab572749bd73", "generation_seconds_batch": 20.583765798946843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.43247127532959, "target_z": 4.124999926057493, "ce": 6.1020402908325195, "genuineness": 4.432034492492676, "identity": 0.7338113188743591, "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_Contentment/d5930e1768247a84fe1641bd9f68a36feb0965d791bb3d93145d43ca0baaa202.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "d5e16e6dfd076a1dabb204a25388d1697ce30967ad5dbb382fa6630ded747c66", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "582bd49bea53fc095ff765a727a80dcabadc593361449e891268db8954539909", "generation_seconds_batch": 22.867872898932546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.149078845977783, "target_z": 3.562500229221771, "ce": 6.229123115539551, "genuineness": 4.507347106933594, "identity": 0.6168783903121948, "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_Contentment/d5e16e6dfd076a1dabb204a25388d1697ce30967ad5dbb382fa6630ded747c66.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": "d5f972aac3a63c67cb2aba3d44450edda6b30daeb9389bb345379ecda9f5fe41", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f9c4d052cdf1dad8445e18308a739dd693c8c9aaecc5791e12cd31ae0ee0c7af", "generation_seconds_batch": 14.634125599986874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6056556701660156, "target_z": 4.468750003697125, "ce": 6.3641486167907715, "genuineness": 4.293961524963379, "identity": 0.6889121532440186, "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_Contentment/d5f972aac3a63c67cb2aba3d44450edda6b30daeb9389bb345379ecda9f5fe41.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": "d684fbb78de1b788a437ad48bb42af51abc311d5153242569ba94199180e401e", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "7e4bfea6c46f908bb7cb8af539199e0bc19d7d8e333df3adbb38696061835e60", "generation_seconds_batch": 14.640034439973533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.164822816848755, "target_z": 3.5937501072166347, "ce": 6.435632705688477, "genuineness": 4.268857479095459, "identity": 0.545219898223877, "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_Contentment/d684fbb78de1b788a437ad48bb42af51abc311d5153242569ba94199180e401e.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "d774cb3aca309d0ea8e6f0ea7c8e17279dbe46667c46fb6fe28c869489b978ad", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "663d8ab9fad416dc65bde01b2e875e14d16562e8cc61354f54e220baac175e1d", "generation_seconds_batch": 22.867872898932546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5584235191345215, "target_z": 4.374999896480491, "ce": 6.292664527893066, "genuineness": 4.20609712600708, "identity": 0.725911021232605, "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_Contentment/d774cb3aca309d0ea8e6f0ea7c8e17279dbe46667c46fb6fe28c869489b978ad.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "d7fafe9f48ba349393f8c5efaa91acefa4f902e43510a0193d21123d9ae04ab9", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "264dde5c9fd8c3bff601f3d6426d89877fdaa67a0d927cc6d463ea040c56d0ba", "generation_seconds_batch": 19.626081667025574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7316079139709473, "target_z": 4.718749974120122, "ce": 6.213237762451172, "genuineness": 3.986435890197754, "identity": 0.2598930597305298, "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_Contentment/d7fafe9f48ba349393f8c5efaa91acefa4f902e43510a0193d21123d9ae04ab9.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "d892d61ca24f527f8cf656ca6c2d09912c2b8d5cb80b253d536817cfd3e7c36a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "03d058fb90545dab97f7ae28068cf2d671acfc1489acbca0bd597a37123c03bb", "generation_seconds_batch": 21.903045715996996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.007382392883301, "target_z": 3.2812499075718664, "ce": 6.316492557525635, "genuineness": 4.65797233581543, "identity": 0.5123124122619629, "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_Contentment/d892d61ca24f527f8cf656ca6c2d09912c2b8d5cb80b253d536817cfd3e7c36a.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "d8c4ba8ea77686e3ef53681d558e8bd014ec7a54ee76fcbccf4407e4b9f01259", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "1d7e401addb027241b69a50cec3bfdcd9b07d13ddf4532778790798660ecb387", "generation_seconds_batch": 19.75815449806396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.212054967880249, "target_z": 3.68750021443327, "ce": 6.475345611572266, "genuineness": 4.406930446624756, "identity": 0.6146718263626099, "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_Contentment/d8c4ba8ea77686e3ef53681d558e8bd014ec7a54ee76fcbccf4407e4b9f01259.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "d961e7675d3ffe4823b6f3e786b10cf8fdafd8e493070c9eb113942668a62e7b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "fb67b0b969d74684b7c432271d853f6b93ab9ef86f91002f0920ce271509df34", "generation_seconds_batch": 20.17940120899584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.54267954826355, "target_z": 4.343750018485626, "ce": 6.181467056274414, "genuineness": 4.632867813110352, "identity": 0.7672322392463684, "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_Contentment/d961e7675d3ffe4823b6f3e786b10cf8fdafd8e493070c9eb113942668a62e7b.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "d9d206ab5520977cf11e66dfcbb72549a9fd0fe6af54a369d9915ae86f3c0c0f", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "5cd583403059d94952ced1b10c6f0fff54f49dd7ace67bda650a548dd3a72e96", "generation_seconds_batch": 22.027468731976114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8105820417404175, "target_z": 2.890625012939939, "ce": 6.109982967376709, "genuineness": 4.168440818786621, "identity": 0.6254758238792419, "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_Contentment/d9d206ab5520977cf11e66dfcbb72549a9fd0fe6af54a369d9915ae86f3c0c0f.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": "d9eb211ac3e5d24a4d08ee615eccc2873234c84bab68f68573d68212d5736565", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The keys are on the kitchen table.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6469417791237e188b7e348ee9a265aea094270615b03b1057964e937269b950", "generation_seconds_batch": 14.495483485981822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.54267954826355, "target_z": 4.343750018485626, "ce": 6.459460258483887, "genuineness": 4.15588903427124, "identity": 0.45555800199508667, "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_Contentment/d9eb211ac3e5d24a4d08ee615eccc2873234c84bab68f68573d68212d5736565.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "da345ec2d10eb28ee0e1961e4c87c0536fbe077f826897916104ef624a327d26", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d643769853bca022636fb587da41825179c9a42d5f11fb75e1d87cb753b4eb07", "generation_seconds_batch": 19.210153987049125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4009833335876465, "target_z": 4.062500170067765, "ce": 6.332377910614014, "genuineness": 4.20609712600708, "identity": 0.2646223306655884, "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_Contentment/da345ec2d10eb28ee0e1961e4c87c0536fbe077f826897916104ef624a327d26.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "daa3d9f3ca6009d4616822ce3def08213f5244ea5880311dc4673031e6d11210", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ccc11bc4cad71f2bc07f5316e00d50b800750127d25a18408b643b91e8945db4", "generation_seconds_batch": 20.481964682927355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0939745903015137, "target_z": 3.4531249463916827, "ce": 6.467403411865234, "genuineness": 4.293961524963379, "identity": 0.6254072189331055, "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_Contentment/daa3d9f3ca6009d4616822ce3def08213f5244ea5880311dc4673031e6d11210.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "daeb45567914503c5645a51cddad21392540761252d83ea1eac7cfa7b84c1481", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "0895db31c411a02fe746d0dea9ddf8dbb3ecd85da3d28ba185d498c933889bde", "generation_seconds_batch": 19.549096547998488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4639594554901123, "target_z": 4.187500155279264, "ce": 6.1894097328186035, "genuineness": 4.344170093536377, "identity": 0.8291574716567993, "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_Contentment/daeb45567914503c5645a51cddad21392540761252d83ea1eac7cfa7b84c1481.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "dafb25939cd05f8f7abcf5da065749507aabc66dde19bf89f4e758f788988872", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "ea7c94622a68a428f0004d06d037acf6ee5c65b9d3fcb370746fc141fd8a1964", "generation_seconds_batch": 23.161915789009072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6528878211975098, "target_z": 4.56250011091376, "ce": 6.4912309646606445, "genuineness": 4.293961524963379, "identity": 0.5343416333198547, "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_Contentment/dafb25939cd05f8f7abcf5da065749507aabc66dde19bf89f4e758f788988872.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "15256666318c9ec929a1b9d6b584816d58931dd9094a0b5822f0acd378881ffe", "generation_seconds_batch": 14.510139674996026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8184540271759033, "target_z": 2.9062499519373706, "ce": 6.332377910614014, "genuineness": 4.18099308013916, "identity": 0.3057469129562378, "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_Contentment/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "db4d40d19d34ed7bf2bde375b3f03ea41106ee701e9199b64df4e78246b04a89", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d2e665da7c598709bad151472769ee771179fb49819bf7e7359c4bb970069d42", "generation_seconds_batch": 14.35594613198191, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.479703426361084, "target_z": 4.218750033274128, "ce": 6.403861999511719, "genuineness": 4.293961524963379, "identity": 0.7757121920585632, "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_Contentment/db4d40d19d34ed7bf2bde375b3f03ea41106ee701e9199b64df4e78246b04a89.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "dbf9afe2d775d0c3fbce3c0eb8c21333148f234eef287a34f48d5f78bea3428b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "60ad2b291201633245b8d4871b6df80984e0befbdd2b231efd1b8679d273acca", "generation_seconds_batch": 19.436959319049492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.101846694946289, "target_z": 3.468750122005136, "ce": 6.086154937744141, "genuineness": 4.036643981933594, "identity": 0.5872483253479004, "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_Contentment/dbf9afe2d775d0c3fbce3c0eb8c21333148f234eef287a34f48d5f78bea3428b.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "dc43514f958767a20e26b68e481aba2b54156eaef36601d3ef93035d8601c62c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "95ae17fcf494513b6ea05f8efc6e1601746f0a3c164db73495d842048a88dff9", "generation_seconds_batch": 19.938610797049478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.574167490005493, "target_z": 4.406249774475354, "ce": 6.197352409362793, "genuineness": 4.532451152801514, "identity": 0.6396526098251343, "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_Contentment/dc43514f958767a20e26b68e481aba2b54156eaef36601d3ef93035d8601c62c.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": "dc4eb5cfa70ad4103e95385ff03b5532d55ee9ffcfd8237fa31b108e5bb6d5b5", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Your message arrived after I had left.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "a9c158501fabcc75e20b18d849ee41e30116ba45aa749c62d64edc18556a1fa7", "generation_seconds_batch": 14.350991728017107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.212054967880249, "target_z": 3.68750021443327, "ce": 6.435632705688477, "genuineness": 4.325342178344727, "identity": 0.2106172889471054, "hypothesis": "Your message arrived after I had left. I read it twice, before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/dc4eb5cfa70ad4103e95385ff03b5532d55ee9ffcfd8237fa31b108e5bb6d5b5.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "dc6fd0ea108041aefee3991b74fe6bddcf72f1c61803b33b8cf293fb4757a1d6", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "544fb267b954951437b4550bd46120013347f32d5e6885e7430a49640f22347a", "generation_seconds_batch": 19.930401496007107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.700119733810425, "target_z": 4.656249744898352, "ce": 6.173524379730225, "genuineness": 4.300237655639648, "identity": 0.4329337775707245, "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_Contentment/dc6fd0ea108041aefee3991b74fe6bddcf72f1c61803b33b8cf293fb4757a1d6.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "dcb259d2737799d3efc31f2570c842f965e21dd2326a007d3902d7bc5a99f73a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "dedbd51850d0e842791cf40209cf87f3d8a8dde0352efb124beb08b9723d3fae", "generation_seconds_batch": 19.825778675964102, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.700119733810425, "target_z": 4.656249744898352, "ce": 6.1894097328186035, "genuineness": 4.344170093536377, "identity": 0.6217426061630249, "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_Contentment/dcb259d2737799d3efc31f2570c842f965e21dd2326a007d3902d7bc5a99f73a.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "dce0a2d334b66eb1463223c9bd8d2c1b31839bea0cd864be283aa6cbe9d74682", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "50ae45cc7dd75387999cf67603244e2d51eaf1ee25dfb2db03d8da26337d1987", "generation_seconds_batch": 22.974822315969504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.212054967880249, "target_z": 3.68750021443327, "ce": 6.24500846862793, "genuineness": 4.162164688110352, "identity": 0.4251260757446289, "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_Contentment/dce0a2d334b66eb1463223c9bd8d2c1b31839bea0cd864be283aa6cbe9d74682.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "dd0a967dc3bf16cfe4732657ad92bc39ea99028b6be80f9d8268585aeeaa1fb1", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "637ccc355e40e47683d793d1a141bf7ba0053cd7518e92aae0c9c90b6287295a", "generation_seconds_batch": 19.570843569003046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.45634126663208, "target_z": 2.1874999186632427, "ce": 6.086154937744141, "genuineness": 4.243753433227539, "identity": 0.6586371660232544, "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_Contentment/dd0a967dc3bf16cfe4732657ad92bc39ea99028b6be80f9d8268585aeeaa1fb1.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "dd20a806bfe689545f0a1fd2bce86e214a2dbed616055a731c977baa3373cd3d", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "db2bdd573715b0a3949dd0a1844f5fdf64646e306d7874f4d45741a38beb968f", "generation_seconds_batch": 19.811024650000036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7948379516601562, "target_z": 2.8593748983290532, "ce": 6.348263263702393, "genuineness": 4.413206577301025, "identity": 0.5658842325210571, "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_Contentment/dd20a806bfe689545f0a1fd2bce86e214a2dbed616055a731c977baa3373cd3d.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "dd26ab82ee9be1331d2f4713504398e257330713222e6644d9f2c13bb51be39e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2b66f6dcb8de948d2d8259c893293c744a7884a14bcc5e09144f90a516a852d5", "generation_seconds_batch": 20.518324925913475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.054614543914795, "target_z": 3.3750000147885015, "ce": 5.982900142669678, "genuineness": 4.13078498840332, "identity": 0.4899311661720276, "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_Contentment/dd26ab82ee9be1331d2f4713504398e257330713222e6644d9f2c13bb51be39e.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "dd26b7c1e0d95930e07a4ca2beb510e990a8ee794c8ea9cb64b5c3e8c0a6431b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "9e4818ac7f2d4227760941920ade110ebc4e0ad86ea77cfdc58128edaa0c9fcc", "generation_seconds_batch": 22.172423996031284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0307445526123047, "target_z": 5.312500022182752, "ce": 6.125868320465088, "genuineness": 4.017816066741943, "identity": 0.7000121474266052, "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_Contentment/dd26b7c1e0d95930e07a4ca2beb510e990a8ee794c8ea9cb64b5c3e8c0a6431b.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "dd8f8a21b6649287f03b79329ffb930397a94145f3fb1d224a3c741c20256afd", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "257f97543f7a1a3fb981c55a1f6877e662edb665ddbbcb78268a47059f4126f3", "generation_seconds_batch": 19.434072269010358, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6610137224197388, "target_z": 2.593749988908624, "ce": 6.1894097328186035, "genuineness": 4.268857479095459, "identity": 0.6716454029083252, "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_Contentment/dd8f8a21b6649287f03b79329ffb930397a94145f3fb1d224a3c741c20256afd.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "ddb74537adaf8b962e8c2ec8ba167bd7716310c150919127f169ad39b0eceb16", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2f720619ea267d22ddf5dd93e89bd3295d8cb26842d26e27c23a815651f03bb5", "generation_seconds_batch": 23.101523864082992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3852391242980957, "target_z": 4.031249818840858, "ce": 6.316492557525635, "genuineness": 4.494794845581055, "identity": 0.6961344480514526, "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_Contentment/ddb74537adaf8b962e8c2ec8ba167bd7716310c150919127f169ad39b0eceb16.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "de119865bdfa4bd18279bbbd8f7ad839a29ab8e26764fd529feb68043d5fcde0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "97b77434fd073bd58be7aecda0b6ef296c827d7794def5ddfa39d00d84aa8454", "generation_seconds_batch": 19.584496905095875, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.416727304458618, "target_z": 4.093750048062629, "ce": 6.165581703186035, "genuineness": 4.293961524963379, "identity": 0.4631459712982178, "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_Contentment/de119865bdfa4bd18279bbbd8f7ad839a29ab8e26764fd529feb68043d5fcde0.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "de6535b974ff81d70c3faaf042cae45137aecd05856985c030b057552781583c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "6f6a0b66808d5abdf464287eba70454c35e409d9b166480e6f31228c5d2110c6", "generation_seconds_batch": 19.656338742002845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.212054967880249, "target_z": 3.68750021443327, "ce": 6.054384231567383, "genuineness": 4.143336772918701, "identity": 0.4814341962337494, "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_Contentment/de6535b974ff81d70c3faaf042cae45137aecd05856985c030b057552781583c.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": "deca22f844a05106ff3dc37a870d8e78bb8198f9fcc27189df3eb651cc57a9d5", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "78d2b56239791cf1a80ce3c2c28dd4fe9ebac924a4d4611e891b319ad3831d52", "generation_seconds_batch": 20.826781076961197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.212054967880249, "target_z": 3.68750021443327, "ce": 6.435632705688477, "genuineness": 4.105680465698242, "identity": 0.2196931391954422, "hypothesis": "Deutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat.", "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_Contentment/deca22f844a05106ff3dc37a870d8e78bb8198f9fcc27189df3eb651cc57a9d5.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "df17b88d114dda7563799bbf7290769b3abaeac0eeb0a3f49b47fdc05fda6923", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4964e23f66b1ced0209c2d1a8ac18627327340559a84af52e2450bcd53aa040b", "generation_seconds_batch": 21.739701717044227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2041828632354736, "target_z": 3.6718750388198163, "ce": 6.2767791748046875, "genuineness": 4.293961524963379, "identity": 0.27983519434928894, "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_Contentment/df17b88d114dda7563799bbf7290769b3abaeac0eeb0a3f49b47fdc05fda6923.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "df4adabed326f75c5d2540da900c9cecca3eca4241db9ce20b1da271c3a596eb", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "26c91b70291197af682bcf93f1e97a67c242ed490d75a1985501a3a91b2a9f76", "generation_seconds_batch": 19.7755003280472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5111913681030273, "target_z": 4.281249789263856, "ce": 6.316492557525635, "genuineness": 4.394378662109375, "identity": 0.3586690127849579, "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_Contentment/df4adabed326f75c5d2540da900c9cecca3eca4241db9ce20b1da271c3a596eb.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": "df9cdf2d5b0188419901c9f76e4761867cdd980a3746ab3b6d24fa33d8052ada", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The road turns left behind the bridge.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a9da17858ab2038b695d46dccc36bc1d6a1ac5c6f4226bd3144045e1fbb8c204", "generation_seconds_batch": 19.348003874067217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2277989387512207, "target_z": 3.7187500924281336, "ce": 6.427689552307129, "genuineness": 3.9676074981689453, "identity": 0.33358699083328247, "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_Contentment/df9cdf2d5b0188419901c9f76e4761867cdd980a3746ab3b6d24fa33d8052ada.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": "dfa359963dcb42bffaaf9bf9ff927d18cb14436ba7120824a4d20315f1f66297", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a8a4fac6e6c88634d7d0b4f9a1fa75b3f75bc5c7043a35c12558428a4f2f582d", "generation_seconds_batch": 14.445381347090006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.589911699295044, "target_z": 4.437500125702262, "ce": 6.300607204437256, "genuineness": 4.532451152801514, "identity": 0.554581344127655, "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_Contentment/dfa359963dcb42bffaaf9bf9ff927d18cb14436ba7120824a4d20315f1f66297.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "e0424a11898834b4c0998c19202adefcd93cb0e3607e5cc0155540776c65f7ab", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "36dea93e68f5d0608dd880f48066b27c37d9fd9e6220823722e3d2d3f3592ff7", "generation_seconds_batch": 19.601129529997706, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.212054967880249, "target_z": 3.68750021443327, "ce": 6.213237762451172, "genuineness": 4.13078498840332, "identity": 0.3947744369506836, "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_Contentment/e0424a11898834b4c0998c19202adefcd93cb0e3607e5cc0155540776c65f7ab.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "e0ba74c6ce91545288159a53206d9ff4ed8f5090a64472624f3d642fe2873e90", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "4ec7012238fb7612d79135b0289748e631510da5576dd87d156ceae95360f48a", "generation_seconds_batch": 14.84521505003795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.275031089782715, "target_z": 3.8125001996447683, "ce": 6.229123115539551, "genuineness": 4.532451152801514, "identity": 0.70212322473526, "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_Contentment/e0ba74c6ce91545288159a53206d9ff4ed8f5090a64472624f3d642fe2873e90.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": "e17fd8af2b02bb6f6cc35fc991a9aafd8dfc5addbe10a7a85b18fef819704fec", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "89ab9bd3294186dd7b08ef382aa3e28e858159ea1e7c812fd5f492a49ee62bcf", "generation_seconds_batch": 14.608003514935263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.141206741333008, "target_z": 3.5468750536083173, "ce": 6.24500846862793, "genuineness": 4.086852550506592, "identity": 0.6353192925453186, "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_Contentment/e17fd8af2b02bb6f6cc35fc991a9aafd8dfc5addbe10a7a85b18fef819704fec.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": "e1b716b40fda4e0ee2c5a05ded2eaf5dbdbff84c6dc2fcbedec0a0f0bf57486e", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a079a5528cfd3cbabc303fa39543d084ff1211d3f6a7e6f670619f615b0bd4ae", "generation_seconds_batch": 14.597186562954448, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2435429096221924, "target_z": 3.7499999704229974, "ce": 6.356205940246582, "genuineness": 4.400654315948486, "identity": 0.7575269937515259, "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_Contentment/e1b716b40fda4e0ee2c5a05ded2eaf5dbdbff84c6dc2fcbedec0a0f0bf57486e.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "e21c566fb0e43cf8a253b401debfb780ef416d4ac46ca937b465b72df32cf89f", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b20312685b9ef92f01ac40a2cd26560f87e40de4dde5a7415bd639bcc1e58aef", "generation_seconds_batch": 22.223138472996652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.101846694946289, "target_z": 3.468750122005136, "ce": 6.038498878479004, "genuineness": 4.030367851257324, "identity": 0.41584524512290955, "hypothesis": "De deuren staan nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/e21c566fb0e43cf8a253b401debfb780ef416d4ac46ca937b465b72df32cf89f.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "e25eb1a936278aada24485de75183b4299494e8a352aa4aa7c8b4106c5316dbf", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "3f84e50b5d458b04deb5010193125e0739b42702ac9d6afe79c522e6f3a33430", "generation_seconds_batch": 15.857073536957614, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0467424392700195, "target_z": 3.3593748391750475, "ce": 6.308549880981445, "genuineness": 4.519899368286133, "identity": 0.6371825337409973, "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_Contentment/e25eb1a936278aada24485de75183b4299494e8a352aa4aa7c8b4106c5316dbf.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "e27979d8338b0b59f311ee56cd91fc68b69d919849e6526dfca334903422f9f4", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d7354b6a3bd8fd8f69b1f2a18e503b1f8288e4e85d6537a342e7a8301c6d5c22", "generation_seconds_batch": 16.83763305505272, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2671589851379395, "target_z": 3.7968750240313147, "ce": 5.974957466125488, "genuineness": 4.20609712600708, "identity": 0.7356934547424316, "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_Contentment/e27979d8338b0b59f311ee56cd91fc68b69d919849e6526dfca334903422f9f4.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "e29df01864ac8e568863298175bdbd22fcb5a107a2735dace7c9f1d44a204bd2", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "db68cc2b523b626003e78afb011c12d3da62651eeb2ca9f0743aefe97a3e24ca", "generation_seconds_batch": 19.434072269010358, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.857814073562622, "target_z": 2.9843748835405517, "ce": 6.213237762451172, "genuineness": 4.419482707977295, "identity": 0.4007979929447174, "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_Contentment/e29df01864ac8e568863298175bdbd22fcb5a107a2735dace7c9f1d44a204bd2.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "e2d0b28cc65a9efc64b156172f4798f4f59be7d0cbb34353ccc24c1890aab762", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "097de82245d6d54cfa3b501473a30e4c26bd45d203518e91aaccbacf8ee2c6c3", "generation_seconds_batch": 20.7740468790289, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9758943319320679, "target_z": 3.2187499149661174, "ce": 6.316492557525635, "genuineness": 4.507347106933594, "identity": 0.6164044141769409, "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_Contentment/e2d0b28cc65a9efc64b156172f4798f4f59be7d0cbb34353ccc24c1890aab762.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "e354bca1e7a677097e35bd89b43915199a100937083c307cc383cbc17edee69e", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "79c33e4c70fbf9380557b33e4003dc654d83e67d5c84142903444d803eb12adf", "generation_seconds_batch": 20.91859691904392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3616230487823486, "target_z": 3.9843747652325407, "ce": 6.157639026641846, "genuineness": 4.18099308013916, "identity": 0.7244049906730652, "hypothesis": "Avoidin Tadafida Batalite. She trouved la petite boite. Elle était prê de la vieille fenêtre.", "wer": 0.7368421052631579, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/e354bca1e7a677097e35bd89b43915199a100937083c307cc383cbc17edee69e.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": "e360eef46a02dd684dad97031130f5f994a02bc6a18ca4905fae62332cdcefdb", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3b57baec122f6578f869f341012f921f5ac68b6edcce5eb122a45bee4a837cec", "generation_seconds_batch": 14.398295005084947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.141206741333008, "target_z": 3.5468750536083173, "ce": 6.205295085906982, "genuineness": 4.268857479095459, "identity": 0.5531061887741089, "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_Contentment/e360eef46a02dd684dad97031130f5f994a02bc6a18ca4905fae62332cdcefdb.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "e3af562c95578d130a67ba212fa4c347f8264b513e15494f5f7cb77dabc146ca", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d9961dfccee113172f36fb8f35b311b14d63ded4850cc05c538e6edf9a192d52", "generation_seconds_batch": 19.78082472400274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3852391242980957, "target_z": 4.031249818840858, "ce": 6.09409761428833, "genuineness": 4.494794845581055, "identity": 0.5926933884620667, "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_Contentment/e3af562c95578d130a67ba212fa4c347f8264b513e15494f5f7cb77dabc146ca.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "e49c4212537a7b5100cfaf785ce7d63f2028f44d3f647f6cf9a00cdb13133cbd", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d76266c6efa2f695e827a02623d8acedf74e9310acc892055d50e4d9fbe7a66d", "generation_seconds_batch": 19.772828968940303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.416727304458618, "target_z": 4.093750048062629, "ce": 6.2767791748046875, "genuineness": 4.331617832183838, "identity": 0.26361364126205444, "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_Contentment/e49c4212537a7b5100cfaf785ce7d63f2028f44d3f647f6cf9a00cdb13133cbd.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": "e4de11988d76034aaf57f122e64b0a086ad9763f35faad022592468300af208a", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "81c9fc9ddb3f56e829d799491dbf813f0ac8b671d3e4486deadc8114c063e747", "generation_seconds_batch": 15.052727816044353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4482152462005615, "target_z": 4.156249804052357, "ce": 6.149696350097656, "genuineness": 4.20609712600708, "identity": 0.4914282262325287, "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_Contentment/e4de11988d76034aaf57f122e64b0a086ad9763f35faad022592468300af208a.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": "e510090aa000baac86453e0299e453129224dfc74778eb135d5bab207c8813d2", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ad421f18a56f251bf0236515382c2fac1c7719a856975e985d3dd2b8d1c09cb4", "generation_seconds_batch": 14.507397134089842, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.369495153427124, "target_z": 3.9999999408459948, "ce": 6.427689552307129, "genuineness": 4.293961524963379, "identity": 0.49283984303474426, "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_Contentment/e510090aa000baac86453e0299e453129224dfc74778eb135d5bab207c8813d2.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "e69670da507f761008b9efb9e02333b3af7005fdfa44984c64ff15b948379dec", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "116ce0f590513d3de24ca01b8395d050a74eb8f0308d6bb15a7911a5fe528db3", "generation_seconds_batch": 19.98108323093038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.416727304458618, "target_z": 4.093750048062629, "ce": 6.252951145172119, "genuineness": 4.137060642242432, "identity": 0.3553389310836792, "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_Contentment/e69670da507f761008b9efb9e02333b3af7005fdfa44984c64ff15b948379dec.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "e6a1cea310f1c88f098dfd5f9d6a8733b95327b4871a2107f655c5fbc1040292", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "9ca1143755ce102f9b6a0fff1eaf02e141d653af1519210b1fbb34822ae234f0", "generation_seconds_batch": 22.7584306220524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.54267954826355, "target_z": 4.343750018485626, "ce": 6.260893821716309, "genuineness": 4.375550270080566, "identity": 0.7167675495147705, "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_Contentment/e6a1cea310f1c88f098dfd5f9d6a8733b95327b4871a2107f655c5fbc1040292.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "e6d8864dfbe3cc43fe671d15960d4e0295df1ec8fc8bc5194fbf82f8a4b011ad", "bucket": "emo_Contentment", "phase": "wording", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "79eaa1e0065ed1468492d9e5d8e3a91e847ee45fcd3581866669e0e55a6dc1d1", "generation_seconds_batch": 15.48966299497988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2831569910049438, "target_z": 1.843750077639632, "ce": 6.205295085906982, "genuineness": 4.381826400756836, "identity": 0.758442223072052, "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_Contentment/e6d8864dfbe3cc43fe671d15960d4e0295df1ec8fc8bc5194fbf82f8a4b011ad.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "d1eff176b9d9b3b0bab43f620b4093a482028a3f58891363899be85df19b5402", "generation_seconds_batch": 14.512034207000397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3852391242980957, "target_z": 4.031249818840858, "ce": 6.443574905395508, "genuineness": 4.419482707977295, "identity": 0.3743076026439667, "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_Contentment/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "e72948d529073dc5ac073856f3663e3fc2fa499d0c4c4ea2ade5ff27e70533c5", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "3ab7eca709e8c70059bb5f9e4e946921172f42eee3890fd320ba6bb9942bf064", "generation_seconds_batch": 20.20043969503604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.141206741333008, "target_z": 3.5468750536083173, "ce": 6.1894097328186035, "genuineness": 4.582659721374512, "identity": 0.7552621364593506, "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_Contentment/e72948d529073dc5ac073856f3663e3fc2fa499d0c4c4ea2ade5ff27e70533c5.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "e749bc0bb133d693071a84a93d9f78e81c20a6131fa1f03969022916ad81cd86", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "8981b6d4de6cc7b40dbf0ff8b1be0af1a0ea3b08c6b173c951df658fae0e8278", "generation_seconds_batch": 20.250623031985015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8971742391586304, "target_z": 3.0625000517597547, "ce": 6.205295085906982, "genuineness": 4.105680465698242, "identity": 0.6661875247955322, "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_Contentment/e749bc0bb133d693071a84a93d9f78e81c20a6131fa1f03969022916ad81cd86.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "e7847901a9a9b9b90fdc6df39c97d3b1180585549ec0dc7da0f5e9b0f9b9b776", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "fe28f28a68266978f8753fd2731ec318f072ac47b5cb74649c5aa19fb88eb082", "generation_seconds_batch": 19.506171619985253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.030998468399048, "target_z": 3.3281249611801837, "ce": 6.141753673553467, "genuineness": 4.6203155517578125, "identity": 0.7788715362548828, "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_Contentment/e7847901a9a9b9b90fdc6df39c97d3b1180585549ec0dc7da0f5e9b0f9b9b776.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "e820c0843013de15face64fbe4bb692c6f8afb81cc771d716c68739d65dfe7ac", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a766e155e341ed1ad7b834a95eac7e73d120931ed2ca1b8a6617d8fee5604a77", "generation_seconds_batch": 19.05873520905152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9758943319320679, "target_z": 3.2187499149661174, "ce": 6.173524379730225, "genuineness": 4.118232727050781, "identity": 0.3949727714061737, "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_Contentment/e820c0843013de15face64fbe4bb692c6f8afb81cc771d716c68739d65dfe7ac.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "e8396a3457ea23bfea223e6ea8ef453ee0c5b9b15c4092a00790685b15495502", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "35a5c48bbc627c5da3b5fb5e25aec447a41e53a30d8315c0bb4102ba2c378a55", "generation_seconds_batch": 21.562577673001215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.54267954826355, "target_z": 4.343750018485626, "ce": 6.403861999511719, "genuineness": 4.444586753845215, "identity": 0.4761848747730255, "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_Contentment/e8396a3457ea23bfea223e6ea8ef453ee0c5b9b15c4092a00790685b15495502.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "e84e848d3dbc9b6e22812a32870f6d41e53b033fa4d45ffdb57e79a32d14e741", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "c7f0bf0014280ab35cc3fd67ec3c225bc398004977f53dcc525022b478f120f0", "generation_seconds_batch": 14.72406321996823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.030998468399048, "target_z": 3.3281249611801837, "ce": 6.086154937744141, "genuineness": 4.124508857727051, "identity": 0.32900160551071167, "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_Contentment/e84e848d3dbc9b6e22812a32870f6d41e53b033fa4d45ffdb57e79a32d14e741.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": "e884f862f240d9919e0d9e7b8501b0f94d0826dffdefd02659b0d4dce8f28921", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Your message arrived after I had left.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5759c52284c55d1cadb06650a106d9350920451e51c1514767fd01aa28004078", "generation_seconds_batch": 14.261590243084356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.479703426361084, "target_z": 4.218750033274128, "ce": 6.372091293334961, "genuineness": 4.2751336097717285, "identity": 0.3361378312110901, "hypothesis": "Your message arrived after I had left. I read it twice, before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/e884f862f240d9919e0d9e7b8501b0f94d0826dffdefd02659b0d4dce8f28921.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "e8b51c6658f5cc2d194152cab070e8ab5f3a9dd2ea12980a6b4477758dc35c0c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "67cd4a2680a38ab1617b6ae96e37d02bbb20b775349a2758be97712db15610b2", "generation_seconds_batch": 15.342227032058872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.007382392883301, "target_z": 3.2812499075718664, "ce": 6.181467056274414, "genuineness": 4.532451152801514, "identity": 0.7516627311706543, "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_Contentment/e8b51c6658f5cc2d194152cab070e8ab5f3a9dd2ea12980a6b4477758dc35c0c.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "e8b7be07ea0face248a6900d708bec69f693f4a53f14147b642c6a25261fe8ce", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "70fcf6f34e043449996ac97e0ae4826ee892443b97291e99ab9013820b268ef0", "generation_seconds_batch": 19.53594679501839, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.526935577392578, "target_z": 4.312500140490763, "ce": 6.157639026641846, "genuineness": 4.2249250411987305, "identity": 0.5043277740478516, "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_Contentment/e8b7be07ea0face248a6900d708bec69f693f4a53f14147b642c6a25261fe8ce.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "e91f376847c715a7268f4817ab029f9022632287dfd2d7bb0414ed9cc275cddd", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "875e8a9dbd435f83857e5598d089367569087429482c110bcb1ae62a1f3b295e", "generation_seconds_batch": 19.577421439928003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3616230487823486, "target_z": 3.9843747652325407, "ce": 6.213237762451172, "genuineness": 3.9173994064331055, "identity": 0.31758785247802734, "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_Contentment/e91f376847c715a7268f4817ab029f9022632287dfd2d7bb0414ed9cc275cddd.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "e936bf475a2390640a0c0cb59626014716a7ac7172cf483838baf4ef9400d9fc", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "642916da16f04a2e4d6a3a840e369353d37afc77e2304032053877fa033991a0", "generation_seconds_batch": 14.903002227074467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6373976469039917, "target_z": 2.5468749353003064, "ce": 6.109982967376709, "genuineness": 4.143336772918701, "identity": 0.7384554147720337, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/e936bf475a2390640a0c0cb59626014716a7ac7172cf483838baf4ef9400d9fc.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "e93ff7437341db88608b3827b2d7c7fee5e54f455a405370afb3f36b70606114", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e136bb445c5e86d99e89361f0ba048958f407360a2fab1e34c422f2344982f81", "generation_seconds_batch": 20.01667128293775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7158639430999756, "target_z": 4.687500096125259, "ce": 6.205295085906982, "genuineness": 4.293961524963379, "identity": 0.815777063369751, "hypothesis": "Ah. J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/e93ff7437341db88608b3827b2d7c7fee5e54f455a405370afb3f36b70606114.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "e9421919e9752225fdc21083251c7e3925d6f65503d4b4d75577de23e420f0d0", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d73df609bd90708db504fda6653e1d5b5703a3035fff3f8d232981b33e861262", "generation_seconds_batch": 20.2394188469043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7630958557128906, "target_z": 4.78124973010985, "ce": 6.395919322967529, "genuineness": 4.319066047668457, "identity": 0.26527857780456543, "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_Contentment/e9421919e9752225fdc21083251c7e3925d6f65503d4b4d75577de23e420f0d0.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "e968ffaaa07d93197931a7307e9d2a23dbf4414420a38036ad10212630219fa4", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "4eaa3bb651d0ddc379373e1d1670201f5e53cdd31214471049f28faf4faf315b", "generation_seconds_batch": 21.133779039955698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.007382392883301, "target_z": 3.2812499075718664, "ce": 6.1894097328186035, "genuineness": 4.168440818786621, "identity": 0.34525784850120544, "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_Contentment/e968ffaaa07d93197931a7307e9d2a23dbf4414420a38036ad10212630219fa4.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "741fd77f4b4a88030c1f6b55c2c20aac580ba378310f26b4d9931c4bb881d62e", "generation_seconds_batch": 16.508516159956343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.834197998046875, "target_z": 2.9374998299322344, "ce": 6.427689552307129, "genuineness": 4.432034492492676, "identity": 0.5295091867446899, "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_Contentment/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "ea6df057031d6e6e886a41471bff0b5eeec555ad0dea3a2ecd3cd22e60dd2ceb", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b1acfd4a70731209c9420b086c148195427199a0ebed13c7a5c5e5a78b7ee385", "generation_seconds_batch": 22.621577456011437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1175906658172607, "target_z": 3.5, "ce": 6.475345611572266, "genuineness": 4.218649387359619, "identity": 0.5248419642448425, "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_Contentment/ea6df057031d6e6e886a41471bff0b5eeec555ad0dea3a2ecd3cd22e60dd2ceb.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "eb6f8a889a42a21ab23d5403d009637140c35121f580736d96e0e05358a8526a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "4e665540b5fa08b6ff54b00dccf9d25a050ebe607531801005f628244575df2b", "generation_seconds_batch": 14.258096136967652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6767576932907104, "target_z": 2.624999866903488, "ce": 6.316492557525635, "genuineness": 4.105680465698242, "identity": 0.6411579251289368, "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_Contentment/eb6f8a889a42a21ab23d5403d009637140c35121f580736d96e0e05358a8526a.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "fd66f9f79440ca9cb9f27e24358fdb1c40becd1a0cac1f4d36a535fa5177e10e", "generation_seconds_batch": 14.783017495064996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40099912881851196, "target_z": 0.09277341543278313, "ce": 6.173524379730225, "genuineness": 4.356721878051758, "identity": 0.6255995035171509, "hypothesis": "La route tourne à gauche après le pont. Continue jusqu'à la petite barrière en bois. Je je t'attendrai de l'autre côté.", "wer": 0.05, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.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": "ece90ee56dff2f7201ca7d089d9a85582b4190b8bff9923d664a71b09199bed4", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bb5206bfab982fd9b6d875a99ecfe70f2cd9f12b122d07c1d4d4b622527cf213", "generation_seconds_batch": 14.522594542941079, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0231266021728516, "target_z": 3.312500258798774, "ce": 6.149696350097656, "genuineness": 4.174716949462891, "identity": 0.7259564399719238, "hypothesis": "Ik schrijf het nummer op de envelop, lees het goed en controleer de laatste twee cijfers. Bel me wanneer je.", "wer": 0.17391304347826086, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/ece90ee56dff2f7201ca7d089d9a85582b4190b8bff9923d664a71b09199bed4.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "ecfb2cca2d64364c0879139dbab6847a8ae43cd8463312bfecd6ae4742491930", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "6ab538aa37a00de3732a27dd3e48a19dfa88f8557eb9425a4253a77ec32c4267", "generation_seconds_batch": 19.965466755907983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6213996410369873, "target_z": 4.4999998816919895, "ce": 6.284721851348877, "genuineness": 4.080576419830322, "identity": 0.5111355781555176, "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_Contentment/ecfb2cca2d64364c0879139dbab6847a8ae43cd8463312bfecd6ae4742491930.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "ed9226064c3ab2d8ee2d379661484d4ffaace8fe06932ea8ab6ebb6122569d64", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "656efd9cc6893dfff8ab6fc1becdcb67e324066d57bba57659a633dd6bd64917", "generation_seconds_batch": 19.982844781014137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3301351070404053, "target_z": 3.921875009242813, "ce": 5.911416053771973, "genuineness": 4.262581825256348, "identity": 0.6313943862915039, "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_Contentment/ed9226064c3ab2d8ee2d379661484d4ffaace8fe06932ea8ab6ebb6122569d64.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "edc39f41a192c9a09fc4818970b6eca197515afe439773ab7c365589e7f01827", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "201838f70c09b8d09d53f7522bee4c5d519c3d15e83be2bd86daea37daa94b52", "generation_seconds_batch": 19.822374399984255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.030998468399048, "target_z": 3.3281249611801837, "ce": 6.2767791748046875, "genuineness": 4.369274139404297, "identity": 0.7193882465362549, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/edc39f41a192c9a09fc4818970b6eca197515afe439773ab7c365589e7f01827.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "ee96e720e4faea4dca694bf57bb0cfb1fe71f223ce2ada45209c6186e6c16f5f", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "09e399603f57599f1fe33caf2e59d7928badcf0b5ea87e351c71fd798b7e03b4", "generation_seconds_batch": 21.561780423042364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.235671043395996, "target_z": 3.734375268041587, "ce": 6.459460258483887, "genuineness": 4.356721878051758, "identity": 0.6446536779403687, "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_Contentment/ee96e720e4faea4dca694bf57bb0cfb1fe71f223ce2ada45209c6186e6c16f5f.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": "eeccbe4fd22ac49d0dc693f99801d126ca1e418563e8a6ad12f11bea6e4fc487", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "89a0a5cfd90dca2a01da8ac8d8c0762fc63084ac715aa945ca11a3b2d02830cd", "generation_seconds_batch": 14.459264880977571, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9992563724517822, "target_z": 5.249999792960981, "ce": 6.356205940246582, "genuineness": 4.356721878051758, "identity": 0.6739805340766907, "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_Contentment/eeccbe4fd22ac49d0dc693f99801d126ca1e418563e8a6ad12f11bea6e4fc487.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "eeef8a654bf596f3382873fa706577e0d6b861548beddc812093a36b44b7b6d9", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "1c6d54fd69bbf41cdb1c4fb2519cdfbc2308f2c2c3f8f35068c6740721a5318d", "generation_seconds_batch": 20.58589483401738, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.637143611907959, "target_z": 4.531249759686853, "ce": 6.427689552307129, "genuineness": 4.231201171875, "identity": 0.33779042959213257, "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_Contentment/eeef8a654bf596f3382873fa706577e0d6b861548beddc812093a36b44b7b6d9.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": "ef03a81fae5623fff8018797568f01c67d5924d2b2cbf8dc353a4a4c4206cb71", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1fb2d9b6a7277ffee624cfadaebf59acc159bd30c41feed8618ddc5e6541797c", "generation_seconds_batch": 19.39140638394747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.212054967880249, "target_z": 3.68750021443327, "ce": 6.316492557525635, "genuineness": 4.193545341491699, "identity": 0.7621991634368896, "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_Contentment/ef03a81fae5623fff8018797568f01c67d5924d2b2cbf8dc353a4a4c4206cb71.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": "ef53319888bc595c9413d995d1d4dd7dbf525459e5a1cc46ddd7a7d088f23d2d", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "23863caf6eae6267f0242e085ad3351c016e8fb7f44060dec15edd75671d679c", "generation_seconds_batch": 19.390290445066057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0861027240753174, "target_z": 3.4375002440102724, "ce": 6.213237762451172, "genuineness": 3.8295347690582275, "identity": 0.4309123754501343, "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_Contentment/ef53319888bc595c9413d995d1d4dd7dbf525459e5a1cc46ddd7a7d088f23d2d.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": "ef54cfb61e4b15aa1f12904b56a8a54e0fab6bb790cd51a12b37082c3aec8959", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "efa7ac3547f0765ed18fce859e069306be3e6c689e1041186658f1a996ce5b06", "generation_seconds_batch": 14.398584791924804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.416727304458618, "target_z": 4.093750048062629, "ce": 6.24500846862793, "genuineness": 4.507347106933594, "identity": 0.6665607690811157, "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_Contentment/ef54cfb61e4b15aa1f12904b56a8a54e0fab6bb790cd51a12b37082c3aec8959.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "f0363a59dd1cc871a25211d6a98159502808f0da25ff22c7da5da507183437c7", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "1eb11b9d31a8750110d38e0d3762d679fcb37e301e97bf1dd0fc38df0088a91b", "generation_seconds_batch": 19.584496905095875, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2041828632354736, "target_z": 3.6718750388198163, "ce": 6.0305562019348145, "genuineness": 4.218649387359619, "identity": 0.5440027713775635, "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_Contentment/f0363a59dd1cc871a25211d6a98159502808f0da25ff22c7da5da507183437c7.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "f05acfd389b798c1094e37a66ae895ac4517bd6c0fb7dab573190bd27614c4f8", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "efde14ab2706805872ed90c9a9fe7dc2d0242a61f792f44ae6bf6ab030d5d021", "generation_seconds_batch": 20.625577620929107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2514150142669678, "target_z": 3.765625146036451, "ce": 6.181467056274414, "genuineness": 4.2249250411987305, "identity": 0.7935994863510132, "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_Contentment/f05acfd389b798c1094e37a66ae895ac4517bd6c0fb7dab573190bd27614c4f8.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "f0f6787f1e5dbab503297cef39732365a63a0f34010f86c4e39dea90967bc2d6", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "0024fffc9d24b6a274312dc9b239b411a2580318c4046e5d0b7cdd1e62a1c7e8", "generation_seconds_batch": 19.994879939011298, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2277989387512207, "target_z": 3.7187500924281336, "ce": 6.284721851348877, "genuineness": 4.871357440948486, "identity": 0.6568008065223694, "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_Contentment/f0f6787f1e5dbab503297cef39732365a63a0f34010f86c4e39dea90967bc2d6.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "f11c8ccd65af2aa073cef18f0741fdee1ac6393e1494e6d0d50c09adab6c9160", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "18fcb7fed4abbc226d8586cedad6c3749a3886c2146b43dab25d580dd9367899", "generation_seconds_batch": 21.12270346004516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7633498907089233, "target_z": 2.7968749057233038, "ce": 6.316492557525635, "genuineness": 4.369274139404297, "identity": 0.6990451216697693, "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_Contentment/f11c8ccd65af2aa073cef18f0741fdee1ac6393e1494e6d0d50c09adab6c9160.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "f12aeefedb64952c2f2dd24bdc62d36b24830b0e934f5f5db0a276c9a273a389", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c6ff747c4374872003825e64efdacf0f612d733f0c209b4bc846f48b34226e24", "generation_seconds_batch": 19.883153354981914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.188438892364502, "target_z": 3.6406251608249525, "ce": 6.38003396987915, "genuineness": 4.20609712600708, "identity": 0.6243915557861328, "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_Contentment/f12aeefedb64952c2f2dd24bdc62d36b24830b0e934f5f5db0a276c9a273a389.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": "f1ca9077453577a317988118fa5ed87fe6cc3fa9733815cf6d94066fb2cffd83", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Escribí el número en el sobre.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "b670639adfd7b0b1945b9c2ce9133eb985e929839f38b32f2ef175509e426032", "generation_seconds_batch": 15.359538275981322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.43247127532959, "target_z": 4.124999926057493, "ce": 6.260893821716309, "genuineness": 4.369274139404297, "identity": 0.6984010934829712, "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_Contentment/f1ca9077453577a317988118fa5ed87fe6cc3fa9733815cf6d94066fb2cffd83.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "966d018568ad221035a5f476b8881bace50c4aacc3be7e087632676bc3c19304", "generation_seconds_batch": 14.583863836945966, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2671589851379395, "target_z": 3.7968750240313147, "ce": 6.09409761428833, "genuineness": 4.482243061065674, "identity": 0.7653062343597412, "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_Contentment/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "f23ff8b858fd0b7ce550d5f23294f08b68660ef0ab4df9969b02bb8d55cc9c74", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d46b8d927bd85365963de89a85db89b5ffe15caf8456149de3351ea7d59a525b", "generation_seconds_batch": 14.495979923987761, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5111913681030273, "target_z": 4.281249789263856, "ce": 5.959072113037109, "genuineness": 4.425758361816406, "identity": 0.7409974932670593, "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_Contentment/f23ff8b858fd0b7ce550d5f23294f08b68660ef0ab4df9969b02bb8d55cc9c74.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "f345c3be711dc7217598e6f4cb6e4dc6ff50f4522e28acaed2a4e21a3ae0422a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "efa7cb9c83714c4fa27e9d746f53b964d65c8fd7aee29914ef190a82e45f0cdc", "generation_seconds_batch": 19.211536013055593, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6213996410369873, "target_z": 4.4999998816919895, "ce": 6.1020402908325195, "genuineness": 4.293961524963379, "identity": 0.6713475584983826, "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_Contentment/f345c3be711dc7217598e6f4cb6e4dc6ff50f4522e28acaed2a4e21a3ae0422a.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "f35143dbc1742d50be8e966f53af8389f5c088a6ca6245e89e64c85ad8dc2405", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d378de6a24358e26ea1aec93ec0c7b6cfcbc4a843de357a8b6a1ad7b294deb18", "generation_seconds_batch": 19.474665535031818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2199268341064453, "target_z": 3.70312491681468, "ce": 6.205295085906982, "genuineness": 4.444586753845215, "identity": 0.5643899440765381, "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_Contentment/f35143dbc1742d50be8e966f53af8389f5c088a6ca6245e89e64c85ad8dc2405.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": "f3a031ffc476e8d2ea20b320dc66822e4dfa22a6b07e8688cdc6b1b3d53dc697", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9719fc6e16126bfcffda8b3bd3cdf9693f62fa6b4c2dca4a572ae072284795fc", "generation_seconds_batch": 14.49359802203253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4639594554901123, "target_z": 4.187500155279264, "ce": 6.4515180587768555, "genuineness": 4.369274139404297, "identity": 0.7134795188903809, "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_Contentment/f3a031ffc476e8d2ea20b320dc66822e4dfa22a6b07e8688cdc6b1b3d53dc697.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "f3c0aa10866653eb3be788a6a90a440f1bcb29155b71c2998a38d96e31e4ecf9", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "6359f2f4bba1bb6d3e31a4a1c1190c6b5d1fc46ede0a1e7d974da2914e10737e", "generation_seconds_batch": 14.611408349010162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0467424392700195, "target_z": 3.3593748391750475, "ce": 6.348263263702393, "genuineness": 4.570107460021973, "identity": 0.49136433005332947, "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_Contentment/f3c0aa10866653eb3be788a6a90a440f1bcb29155b71c2998a38d96e31e4ecf9.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": "f3d4b975aeefd0aaff3bbcff80a0faf040f3a10c4b93e21771725f9e851365bd", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The keys are on the kitchen table.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "402617af298ded8b207f6e01ea1d01b54c2d1a72fe96613843e5d6d5518cfadf", "generation_seconds_batch": 15.009638322982937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6686317920684814, "target_z": 4.593749988908624, "ce": 6.23706579208374, "genuineness": 3.7291181087493896, "identity": 0.3126492500305176, "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_Contentment/f3d4b975aeefd0aaff3bbcff80a0faf040f3a10c4b93e21771725f9e851365bd.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": "f42737c9a374eaddf0cf590ae925b74a70124e583e91ccf11f6a8c8299125f48", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "28c43960711e3f938889db34d92b86b50b05bd0a67ad5c8d6ec2ca9baca660f4", "generation_seconds_batch": 14.724216460017487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.188438892364502, "target_z": 3.6406251608249525, "ce": 6.157639026641846, "genuineness": 4.2751336097717285, "identity": 0.709415078163147, "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_Contentment/f42737c9a374eaddf0cf590ae925b74a70124e583e91ccf11f6a8c8299125f48.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": "f435982878c20f4b187cad28fa4496a803dad1ff62761371e1d0c83786eeb68f", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The keys are on the kitchen table.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "3e811e227df05ae594a232425ff227b7acf4dce0472c9c8309a37ad3a4a7d547", "generation_seconds_batch": 15.009638322982937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6686317920684814, "target_z": 4.593749988908624, "ce": 6.38797664642334, "genuineness": 3.835810661315918, "identity": 0.27186644077301025, "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_Contentment/f435982878c20f4b187cad28fa4496a803dad1ff62761371e1d0c83786eeb68f.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "f4368ff5da47cf01b8ee99b42b220af6b02b89d3363c45efe9a836d0d9d79cf6", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "f7df4b0fb15b1e70377a2e64ac4d0cc57fcf87a6438e9fedee1a63f846006d17", "generation_seconds_batch": 14.461725878994912, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3380072116851807, "target_z": 3.937500184856267, "ce": 6.427689552307129, "genuineness": 4.143336772918701, "identity": 0.611682653427124, "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_Contentment/f4368ff5da47cf01b8ee99b42b220af6b02b89d3363c45efe9a836d0d9d79cf6.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "f4e6799ac73aba9e00e99b6c11c90ade279b426fe38ee874343872154a5668b7", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "bad2f7ede754dd505aa88c87ea1672327c02b4e3d5ecfcdd2350eb4c77c43b3e", "generation_seconds_batch": 21.260849826969206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4954473972320557, "target_z": 4.249999911268992, "ce": 6.24500846862793, "genuineness": 3.986435890197754, "identity": 0.32638904452323914, "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_Contentment/f4e6799ac73aba9e00e99b6c11c90ade279b426fe38ee874343872154a5668b7.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": "f51ab7afb8f9933a501e87120775ff214c53b32d603b4001fcbc9b957ad90d69", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "34649fefce0c4b50bc5b017f43c95abca2f5d4690662fc16346120974b7f3393", "generation_seconds_batch": 14.936294966028072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1569507122039795, "target_z": 3.578124931603181, "ce": 6.2767791748046875, "genuineness": 4.331617832183838, "identity": 0.5908422470092773, "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_Contentment/f51ab7afb8f9933a501e87120775ff214c53b32d603b4001fcbc9b957ad90d69.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": "f52226a601b773c07a818fd5f69b3ba287b91152b7aea7b6ee946c1e3f57866c", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Your message arrived after I had left.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b95ebf304e1c6dfbeeae7ac973c69f57441dc723e3f3f3c30cbda9ef200fe094", "generation_seconds_batch": 19.15924824902322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.282902956008911, "target_z": 3.8281249020261785, "ce": 6.459460258483887, "genuineness": 4.306513786315918, "identity": 0.06958150863647461, "hypothesis": "Your message arrived after I had left. I read it twice, before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/f52226a601b773c07a818fd5f69b3ba287b91152b7aea7b6ee946c1e3f57866c.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "f538219f974d5fb695552dc609dc38885aa3477369c51aeb106f857f4922d49c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "6802bfeceb4c738161d081640236173c7b4acf1a7cb7268ff449519b0720d895", "generation_seconds_batch": 14.973213821067475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.235671043395996, "target_z": 3.734375268041587, "ce": 6.133810997009277, "genuineness": 3.886019229888916, "identity": 0.27784210443496704, "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_Contentment/f538219f974d5fb695552dc609dc38885aa3477369c51aeb106f857f4922d49c.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": "f5c85b30b877bfc0cf684942a4eb2efdf72b65cff10951de67b2cb2bbc203fa3", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The road turns left behind the bridge.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "7fd3a269ae63bb4280af9c6b3829958ffa00dfb4916e4af311fa8ec777a803f9", "generation_seconds_batch": 14.374462175997905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2435429096221924, "target_z": 3.7499999704229974, "ce": 6.419747352600098, "genuineness": 4.168440818786621, "identity": 0.05633825436234474, "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_Contentment/f5c85b30b877bfc0cf684942a4eb2efdf72b65cff10951de67b2cb2bbc203fa3.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "f61ec2fe8d2067e0ae792bb2f7112a10a48d8b50afb49df144ba613912d3d226", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "ad9be84d11db1d0159ec839512554809cdca4f852107acad648a94c149a76e5d", "generation_seconds_batch": 20.167380071012303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0624866485595703, "target_z": 3.390625190401955, "ce": 6.181467056274414, "genuineness": 4.168440818786621, "identity": 0.556243360042572, "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_Contentment/f61ec2fe8d2067e0ae792bb2f7112a10a48d8b50afb49df144ba613912d3d226.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "f62036d0d8bd4f2896182bf147b8c38d735583279ad0a0218b7d1f200721e70c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "9f3678c6f8647521c053ac766154c33fac25af6bbb2eabc66f93a194d4325908", "generation_seconds_batch": 14.44584268797189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2435429096221924, "target_z": 3.7499999704229974, "ce": 6.221180438995361, "genuineness": 4.344170093536377, "identity": 0.5419859886169434, "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_Contentment/f62036d0d8bd4f2896182bf147b8c38d735583279ad0a0218b7d1f200721e70c.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": "f63153f0b7fde8f8b05b36f35c0dac6ab8c5d634ee1ecdce068836905b68c630", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Someone moved the little blue chair.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "8f499cb3a1fb4b080f7c3978786e73c8eaf61962f194dc71cf61752d7cd85756", "generation_seconds_batch": 14.603631907957606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.526935577392578, "target_z": 4.312500140490763, "ce": 6.499174118041992, "genuineness": 4.20609712600708, "identity": 0.27322471141815186, "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_Contentment/f63153f0b7fde8f8b05b36f35c0dac6ab8c5d634ee1ecdce068836905b68c630.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": "f696fdd035d740ace46e7c2bd5dd287b0db3a7cd87cea509db3310d8ffadffbb", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "e11ea9413592d9fa3b8cc513ceb1552e1f0fa90b662d4c887d27025c0ad875a8", "generation_seconds_batch": 14.570193815976381, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2277989387512207, "target_z": 3.7187500924281336, "ce": 6.109982967376709, "genuineness": 4.369274139404297, "identity": 0.7194911241531372, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis-le bien et verfie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/f696fdd035d740ace46e7c2bd5dd287b0db3a7cd87cea509db3310d8ffadffbb.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": "f723037f2452eb9d840fd83bf4121276289adbe88210e85950f6434875f94467", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "5fdac6b2154f04030744ea6370dab718b986c34dda7943bf4c2fd797270271e2", "generation_seconds_batch": 14.724216460017487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8105820417404175, "target_z": 2.890625012939939, "ce": 6.316492557525635, "genuineness": 4.432034492492676, "identity": 0.7244076728820801, "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_Contentment/f723037f2452eb9d840fd83bf4121276289adbe88210e85950f6434875f94467.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "f7883cb40d8a7aa730cc35561ef5dd65160172fdf91f9296966d3ef8007d2e3b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "2443366f2b61a71ddd7e75accf0e74ff1e9a6548e575f4e9ec8c94e499c38942", "generation_seconds_batch": 19.578423509025015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0467424392700195, "target_z": 3.3593748391750475, "ce": 6.284721851348877, "genuineness": 4.268857479095459, "identity": 0.5248134136199951, "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_Contentment/f7883cb40d8a7aa730cc35561ef5dd65160172fdf91f9296966d3ef8007d2e3b.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "cd51b6436c29b5a9ac3647e67b6d36ed9960918c454eb4d70eb6afee72362697", "generation_seconds_batch": 14.811049113050103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1805667877197266, "target_z": 3.6249999852114985, "ce": 6.125868320465088, "genuineness": 4.6203155517578125, "identity": 0.7263222932815552, "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_Contentment/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.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_Contentment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": "10b4a1beb577acf59557912caeb7a8ff2625c488303a0ce75e30e2610efbf518", "generation_seconds_batch": 16.40034889895469, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.101846694946289, "target_z": 3.468750122005136, "ce": 6.260893821716309, "genuineness": 4.20609712600708, "identity": 0.6855111122131348, "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_Contentment/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "f880bdc5cafbd55f69a8de251d5a167ec0c53278db1ccb6a6bc8eeeead1adc3b", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "692c10a8c5e5fabd0c2e3548b926cb6d6af257e40ef291d79daf904192f0b36b", "generation_seconds_batch": 19.590780700091273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.991638422012329, "target_z": 3.2500000295770026, "ce": 6.348263263702393, "genuineness": 4.607763767242432, "identity": 0.4503251314163208, "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_Contentment/f880bdc5cafbd55f69a8de251d5a167ec0c53278db1ccb6a6bc8eeeead1adc3b.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "f8b704571a3eb7fea4de144ab186d2966db7015661ca8c4d83730a28fc635a74", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2b8d5d5f9c70d58198cfc192624e16ac24942e212b2e0cf975fa7f9d41643d9f", "generation_seconds_batch": 16.849004243966192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.416727304458618, "target_z": 4.093750048062629, "ce": 6.205295085906982, "genuineness": 4.469690799713135, "identity": 0.7750368714332581, "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_Contentment/f8b704571a3eb7fea4de144ab186d2966db7015661ca8c4d83730a28fc635a74.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": "f8bf5f2101dca6c20bbe56e1e12b3caef93a09161875efe6fecc5f82743ccee7", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "638bf422b8b56fe9c389141b9c7f4c557175fea3cab1351ea13f83a7fc7a7e4f", "generation_seconds_batch": 19.14446932799183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8971742391586304, "target_z": 3.0625000517597547, "ce": 6.117925643920898, "genuineness": 4.306513786315918, "identity": 0.46267110109329224, "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_Contentment/f8bf5f2101dca6c20bbe56e1e12b3caef93a09161875efe6fecc5f82743ccee7.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "f8df49771d5ad80a6cb3a25ec8f889ec673c738691f8d53cd1912991bd9de65c", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "d96ae46a670b7a630c27405401c460b98a8f93574cf3256ab711e1ade0ec438c", "generation_seconds_batch": 19.657666228013113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.43247127532959, "target_z": 4.124999926057493, "ce": 6.38797664642334, "genuineness": 4.457139015197754, "identity": 0.42601412534713745, "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_Contentment/f8df49771d5ad80a6cb3a25ec8f889ec673c738691f8d53cd1912991bd9de65c.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "f8f020d794ac735310b83b60bc06e0fc029ad0ccb913120effb3b44bbdbb3a5d", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a4b4fca9a553d1d696aada230fe1189cfe17b58c2790b7abd9b3b64698c0a971", "generation_seconds_batch": 14.72406321996823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7633498907089233, "target_z": 2.7968749057233038, "ce": 5.919358730316162, "genuineness": 4.174716949462891, "identity": 0.7162522077560425, "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_Contentment/f8f020d794ac735310b83b60bc06e0fc029ad0ccb913120effb3b44bbdbb3a5d.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "f9939dbf4a4db5c48837b501cc0d0bdcc16b8b7a8a45990736bfba96c1898fde", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "31b742273e75567d3e95753ef8d0eaac3389090f6363ecf9c9e865fee7c1d7e9", "generation_seconds_batch": 20.060054392088205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4482152462005615, "target_z": 4.156249804052357, "ce": 6.141753673553467, "genuineness": 4.6956281661987305, "identity": 0.710875391960144, "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_Contentment/f9939dbf4a4db5c48837b501cc0d0bdcc16b8b7a8a45990736bfba96c1898fde.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "f9ce711d1200b779e8e06ed9dcae56285bb7da5651b151c3dee0efe5e89b16a7", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "8c1af13a3e755f30b8101a8aff3e07f012ff1e9b69596a9767fde478d168837d", "generation_seconds_batch": 19.59923379297834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9522782564163208, "target_z": 3.1718748613577996, "ce": 6.268836498260498, "genuineness": 4.174716949462891, "identity": 0.8289358615875244, "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_Contentment/f9ce711d1200b779e8e06ed9dcae56285bb7da5651b151c3dee0efe5e89b16a7.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "fa225bb1ed4f302e48b5261bcdbad4464a7e450c250131524c94fbbaae1db887", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "7566b75ee490d6c2d585df55d5edb20f416ce1dc6fd85bb5777254a1f8b59d90", "generation_seconds_batch": 20.61819623201154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0231266021728516, "target_z": 3.312500258798774, "ce": 6.292664527893066, "genuineness": 4.005263805389404, "identity": 0.6682770252227783, "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_Contentment/fa225bb1ed4f302e48b5261bcdbad4464a7e450c250131524c94fbbaae1db887.mp3" }, { "id": "emo_Contentment-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_Contentment-es-1", "key": "fa3f01a131fc79a4831c2bc0a90c67d61099298221c1f98a0bf91125bdae9b10", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] He encontrado la cajita.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "17445bdafe10b053f26cb753985b3ea854706e46939ae9127aede14a57220838", "generation_seconds_batch": 15.221701854025014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.574167490005493, "target_z": 4.406249774475354, "ce": 6.1894097328186035, "genuineness": 4.362998008728027, "identity": 0.5365278720855713, "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_Contentment/fa3f01a131fc79a4831c2bc0a90c67d61099298221c1f98a0bf91125bdae9b10.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "fa43949709058eb0a364d8e9c7d399e4d552f1594bb57bd8610de761582a6572", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "83ff95b5425f1e625ec3f1b3cfced5c2a22eaa491b2a57a12d4ed3abd3031bb0", "generation_seconds_batch": 21.90929864696227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.834197998046875, "target_z": 2.9374998299322344, "ce": 6.133810997009277, "genuineness": 4.042920112609863, "identity": 0.5941218137741089, "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_Contentment/fa43949709058eb0a364d8e9c7d399e4d552f1594bb57bd8610de761582a6572.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": "fa4b5bbea713049fc8730288173825801fe64e3d0ad1916d9a4f1f21afd0ec77", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "623542d8d0f9d137301f6bcfd5235923dd52b2d732b8207258dff18d11104475", "generation_seconds_batch": 14.429919424001127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9050462245941162, "target_z": 3.078124990757187, "ce": 6.197352409362793, "genuineness": 4.281409740447998, "identity": 0.6733405590057373, "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_Contentment/fa4b5bbea713049fc8730288173825801fe64e3d0ad1916d9a4f1f21afd0ec77.mp3" }, { "id": "emo_Contentment-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_Contentment-es-0", "key": "fa7234e3799405e8caa750d9ad5e29ace5a018474309f40cdabae7a8cc920204", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La puerta sigue abierta.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "517e44094be5a481d6d338e8caa1fa6364999edb9085a33a848553ba2990f3a4", "generation_seconds_batch": 19.69721358199604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0388705730438232, "target_z": 3.3437501367936378, "ce": 6.046441555023193, "genuineness": 3.986435890197754, "identity": 0.44018030166625977, "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_Contentment/fa7234e3799405e8caa750d9ad5e29ace5a018474309f40cdabae7a8cc920204.mp3" }, { "id": "emo_Contentment-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_Contentment-en-0", "key": "fb141049a63e693f432e0635feb2a093454884ddb8acffcc5d50d35aae3bd9dc", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] The door is still open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "8141fe979f80d7af37d337fec7c07e910204c85cf4ffcb233e02c250e1297a81", "generation_seconds_batch": 14.494227676070295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.43247127532959, "target_z": 4.124999926057493, "ce": 6.316492557525635, "genuineness": 4.093128204345703, "identity": 0.19671732187271118, "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_Contentment/fb141049a63e693f432e0635feb2a093454884ddb8acffcc5d50d35aae3bd9dc.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "fb31a086545ffd18f388fa023a6ecd77296e715e7245a96fbc7cb79a569e7c7f", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "21c25b5931afe68ca6bbdfb34d642a37e6984930f1e764526c3e479fc2dfbe9b", "generation_seconds_batch": 14.964102057972923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6213996410369873, "target_z": 4.4999998816919895, "ce": 6.268836498260498, "genuineness": 4.3881025314331055, "identity": 0.5369918942451477, "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_Contentment/fb31a086545ffd18f388fa023a6ecd77296e715e7245a96fbc7cb79a569e7c7f.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": "fb8daa863bd3f6cd887bd92f2e95b1bf10a9cb778d44093039dc76757a5c44ec", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "84515afeb1428c80eee45f25615d25d230097e78adf2645b1c55ae0b0a27b0e7", "generation_seconds_batch": 14.607252871035598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.275031089782715, "target_z": 3.8125001996447683, "ce": 6.38797664642334, "genuineness": 4.268857479095459, "identity": 0.45040827989578247, "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_Contentment/fb8daa863bd3f6cd887bd92f2e95b1bf10a9cb778d44093039dc76757a5c44ec.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "fbbee90e050a6c97ffbd429d17895d7c521c87ec14d69028f60e89bc9e29e627", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc22c410df6cfccb796f9dac212667bee66ac7d67c2386b133f35b85e7059647", "generation_seconds_batch": 23.98244228796102, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4639594554901123, "target_z": 4.187500155279264, "ce": 6.006728172302246, "genuineness": 4.143336772918701, "identity": 0.3779580593109131, "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_Contentment/fbbee90e050a6c97ffbd429d17895d7c521c87ec14d69028f60e89bc9e29e627.mp3" }, { "id": "emo_Contentment-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_Contentment-en-1", "key": "fc101ffa350f92edce93e1050b7b79c10f17327de7f41fc8f74c4a99bc3be5d5", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] I found the little box.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] It was beside the old window.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "7b7fe2a1f903330ef838f509666a6704100a49bac189d043511077b739b7b3c5", "generation_seconds_batch": 20.746104321908206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.574167490005493, "target_z": 4.406249774475354, "ce": 6.24500846862793, "genuineness": 3.948779582977295, "identity": 0.4768504500389099, "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_Contentment/fc101ffa350f92edce93e1050b7b79c10f17327de7f41fc8f74c4a99bc3be5d5.mp3" }, { "id": "emo_Contentment-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_Contentment-de-0", "key": "fc309eb680c7c167faa325fda87060d328f5b9a0a35b6885a6e4487abae8011a", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Die Tür ist noch offen.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "86d8eb67269a24a5ee444d9a4e19fe4d8f3c394554e594b00ad56ea53eb5793f", "generation_seconds_batch": 19.233606011024676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.101846694946289, "target_z": 3.468750122005136, "ce": 6.340320587158203, "genuineness": 4.519899368286133, "identity": 0.4829277992248535, "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_Contentment/fc309eb680c7c167faa325fda87060d328f5b9a0a35b6885a6e4487abae8011a.mp3" }, { "id": "emo_Contentment-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_Contentment-de-1", "key": "fc69819217cbadd7b622bb9ca16d109fc1d48d8f029f739f8a7dff482f55f657", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bd01c89d6428ec9e0091e9075243bfcd2dfe2eeda2cf0fb6774a3178df19855d", "generation_seconds_batch": 19.75815449806396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.030998468399048, "target_z": 3.3281249611801837, "ce": 6.300607204437256, "genuineness": 4.068024158477783, "identity": 0.5885084867477417, "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_Contentment/fc69819217cbadd7b622bb9ca16d109fc1d48d8f029f739f8a7dff482f55f657.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-1", "key": "fd02a58e81616d32e3e03a2503c3f9827f27177e31bffcf0c910dc04027a9980", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "1701b50c70d7ea3b7bc72701a1069d1f138f65ec770136a495fe19dca7dd9797", "generation_seconds_batch": 19.540189780993387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7630958557128906, "target_z": 4.78124973010985, "ce": 6.24500846862793, "genuineness": 4.419482707977295, "identity": 0.747941255569458, "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_Contentment/fd02a58e81616d32e3e03a2503c3f9827f27177e31bffcf0c910dc04027a9980.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": "fd9657bfd703c4f489c2c0966c4524e9db6bb7a205e7ff3cd13b54b50c1d380f", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "796d29e11a73135577f359e0fb8b360d9c72c60f8f74eee297f3e261b900cb54", "generation_seconds_batch": 14.390597870922647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1333346366882324, "target_z": 3.531249877994864, "ce": 6.260893821716309, "genuineness": 4.18099308013916, "identity": 0.6791872382164001, "hypothesis": "Calco the petition. Elle is pretty la grand bibliothek. Now remettrums after the dejeuner.", "wer": 0.9047619047619048, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Contentment/fd9657bfd703c4f489c2c0966c4524e9db6bb7a205e7ff3cd13b54b50c1d380f.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "fdaea22560946d6aad61827a19a08eeb2059fdd79b83a96c5099efbfa91355d3", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "3cba34ca0e04eb9f16d4cc4ee482f3167d3d181883f7cc9ee354fb394f181f4b", "generation_seconds_batch": 19.656338742002845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7554779052734375, "target_z": 2.781249966725872, "ce": 6.165581703186035, "genuineness": 4.425758361816406, "identity": 0.4149785041809082, "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_Contentment/fdaea22560946d6aad61827a19a08eeb2059fdd79b83a96c5099efbfa91355d3.mp3" }, { "id": "emo_Contentment-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_Contentment-fr-0", "key": "fe5738022f795f0590b6fee0ffbafdca8166c02976942ffcee2c4e58d8e3c474", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La porte est encore ouverte.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "a88a6c1099daf3722b33ded0fb49dd810a1b3e38183bf26c2b06193b3bcb2763", "generation_seconds_batch": 20.591204055934213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2514150142669678, "target_z": 3.765625146036451, "ce": 6.23706579208374, "genuineness": 4.545003414154053, "identity": 0.7568097710609436, "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_Contentment/fe5738022f795f0590b6fee0ffbafdca8166c02976942ffcee2c4e58d8e3c474.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-0", "key": "fec29f4187c61758ceee3129949f30fa7a0a55d09c5025dc56298d5a7f4ebf65", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] De deur staat nog open.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "caca956d24e2f2938cc5c24899c3eea57a37b799bf805124052be2110871da20", "generation_seconds_batch": 14.160302937030792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8420701026916504, "target_z": 2.953125005545688, "ce": 6.23706579208374, "genuineness": 4.469690799713135, "identity": 0.700086772441864, "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_Contentment/fec29f4187c61758ceee3129949f30fa7a0a55d09c5025dc56298d5a7f4ebf65.mp3" }, { "id": "emo_Contentment-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_Contentment-nl-1", "key": "ff62e4b34f41fe0337082a6fc48e0b947007eda17141892912634bb437ad2b33", "bucket": "emo_Contentment", "phase": "grid", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": "06b61225e7c6ebf1a9737b61a904d6f860bc22b78aa3243e950ede0607f1ea38", "generation_seconds_batch": 21.409804883995093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.944406270980835, "target_z": 3.156249922360368, "ce": 6.24500846862793, "genuineness": 4.344170093536377, "identity": 0.6145956516265869, "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_Contentment/ff62e4b34f41fe0337082a6fc48e0b947007eda17141892912634bb437ad2b33.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": "ff8261565c11a1b5ad1ae4bf6b1fd225b13b5cd579b766840c34ea6642b775f3", "bucket": "emo_Contentment", "phase": "heldout", "candidate": "manual-e34e2073bf7b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Start with a near-whisper quality that immediately builds into a rich, comforting mid-range tone, implying shared tranquility.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Employ a very slight, almost imperceptible vocal fry on key consonants to enhance the sense of settled, deep comfort.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude the speech with a sustained, resonant tone that lingers slightly beyond the last word, like a warm echo.) [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": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8b169a8f1edd975ab7eb9b7b7165191e7d712d2400531c1e32376926c2121614", "generation_seconds_batch": 19.287631756975316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4639594554901123, "target_z": 4.187500155279264, "ce": 6.252951145172119, "genuineness": 4.325342178344727, "identity": 0.6498116254806519, "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_Contentment/ff8261565c11a1b5ad1ae4bf6b1fd225b13b5cd579b766840c34ea6642b775f3.mp3" }, { "key": "original-emo_Contentment-de-0-seed1701-scale0.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "53b8c96d1e64b873461245e3b85d5620985a777581b457b130463f26a2b369b6", "task_id": "emo_Contentment-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.7318618297576904, "target_z": 2.7343749131175543, "ce": 6.38797664642334, "genuineness": 4.168440818786621, "identity": 0.5821243524551392, "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_Contentment/de/fb32a1859f27f8cd1e98a916.mp3" }, { "key": "original-emo_Contentment-de-0-seed1701-scale0.5", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "6ce8f3126353e6a3e16ee2403b44eb5999d7ac1c7601ba94ea818f18fa20f54e", "task_id": "emo_Contentment-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.5271893739700317, "target_z": 2.3281248428721733, "ce": 6.141753673553467, "genuineness": 4.406930446624756, "identity": 0.5228237509727478, "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_Contentment/de/c66d24d8942d50866641039a.mp3" }, { "key": "original-emo_Contentment-de-0-seed1701-scale0.75", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "d54bc8ba46ef03b78b628c9e47387ad61765a2cd3adbe0c000fdb9f7aa684ac1", "task_id": "emo_Contentment-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.7239898443222046, "target_z": 2.7187499741201226, "ce": 6.300607204437256, "genuineness": 4.595211505889893, "identity": 0.5321959257125854, "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_Contentment/de/6a223dece72ba843a1d157c2.mp3" }, { "key": "original-emo_Contentment-de-0-seed1701-scale1.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "247bfe557862642b20cd434c80a4e1d328f05e6b659b8fb8bb9127f6ddb44b22", "task_id": "emo_Contentment-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.5350614786148071, "target_z": 2.343750018485627, "ce": 6.141753673553467, "genuineness": 4.394378662109375, "identity": 0.5138921737670898, "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_Contentment/de/3dd4c13122cc0efd238a84b0.mp3" }, { "key": "original-emo_Contentment-de-0-seed1702-scale0.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "c9ea45255e3544cb1eca3444f7c2b97ee28e7f6d523fdd546e371dee6ef83d4e", "task_id": "emo_Contentment-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.4169812202453613, "target_z": 2.109374987060061, "ce": 6.213237762451172, "genuineness": 4.231201171875, "identity": 0.5269575715065002, "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_Contentment/de/fde30eb5f36a40fb407d1abb.mp3" }, { "key": "original-emo_Contentment-de-0-seed1702-scale0.5", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "513f8c4e5d407787ab2f1089b7ab5cdca14275eeb8a977da2fba6eeb73d75418", "task_id": "emo_Contentment-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.6846297979354858, "target_z": 2.6406250425169415, "ce": 6.133810997009277, "genuineness": 4.519899368286133, "identity": 0.5112199783325195, "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_Contentment/de/d8345ad74b4edb38c900a532.mp3" }, { "key": "original-emo_Contentment-de-0-seed1702-scale0.75", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "48ae70c1b25b0206187e6cfbd211934ca5e43d21b858ce22d8a0a7fcb11edf2c", "task_id": "emo_Contentment-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.9050462245941162, "target_z": 3.078124990757187, "ce": 6.165581703186035, "genuineness": 4.457139015197754, "identity": 0.5637553930282593, "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_Contentment/de/39e81d129b7624ce854f49b8.mp3" }, { "key": "original-emo_Contentment-de-0-seed1702-scale1.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "d23198c7ede4118ea76c7977413ff2acc919973e88508d25f5d6c85aba3128c7", "task_id": "emo_Contentment-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.3776211738586426, "target_z": 2.03125005545688, "ce": 6.252951145172119, "genuineness": 4.400654315948486, "identity": 0.7207728624343872, "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_Contentment/de/3e400f72fa1739d2f880833a.mp3" }, { "key": "original-emo_Contentment-de-1-seed1701-scale0.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "84a6c88253715cb5c7f0b9d50565b0cede3f90cd01bdfba59c2fa560d9694c78", "task_id": "emo_Contentment-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.0388705730438232, "target_z": 3.3437501367936378, "ce": 6.41180419921875, "genuineness": 4.293961524963379, "identity": 0.4902801513671875, "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_Contentment/de/dbc8addb8c5242d999f2884b.mp3" }, { "key": "original-emo_Contentment-de-1-seed1701-scale0.5", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "c25f3b23124a3f1c35c447bc70103ae15c12bf3c9801ec29781429eb97489385", "task_id": "emo_Contentment-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.8814301490783691, "target_z": 3.031249937148869, "ce": 6.316492557525635, "genuineness": 4.2374773025512695, "identity": 0.44589298963546753, "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_Contentment/de/132cda9e0274c68ae85b153c.mp3" }, { "key": "original-emo_Contentment-de-1-seed1701-scale0.75", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "ac8730e9666b71c17f95f6d2f9d258803447da2c458d27d64726a725c3edee2b", "task_id": "emo_Contentment-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.125462770462036, "target_z": 3.5156251756134536, "ce": 6.38003396987915, "genuineness": 4.331617832183838, "identity": 0.6963412761688232, "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_Contentment/de/784937285543181fcdd686d6.mp3" }, { "key": "original-emo_Contentment-de-1-seed1701-scale1.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "eec58257dee823dbcdedbd571255a7a6d86745d431583956ad666cb0d92b8a65", "task_id": "emo_Contentment-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.0231266021728516, "target_z": 3.312500258798774, "ce": 6.38003396987915, "genuineness": 4.193545341491699, "identity": 0.5879607200622559, "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_Contentment/de/7923e06ac677b2feb51e819f.mp3" }, { "key": "original-emo_Contentment-de-1-seed1702-scale0.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "7e8df40f3d9ca9cf05d9db372c93dc4fde10a8bc2b79b6450cebadb1da670f91", "task_id": "emo_Contentment-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.944406270980835, "target_z": 3.156249922360368, "ce": 6.41180419921875, "genuineness": 4.118232727050781, "identity": 0.4161345958709717, "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_Contentment/de/e9c620662aa83370c9694133.mp3" }, { "key": "original-emo_Contentment-de-1-seed1702-scale0.5", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "f88717c3b64096846f4dbc0c91969d868dbdce8efe3dc47b15fdccbccfc8200a", "task_id": "emo_Contentment-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.0624866485595703, "target_z": 3.390625190401955, "ce": 6.41180419921875, "genuineness": 4.20609712600708, "identity": 0.5750163793563843, "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_Contentment/de/7d1c4d14e6cb187f9ce7493b.mp3" }, { "key": "original-emo_Contentment-de-1-seed1702-scale0.75", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "e81f1472ed5663c6dd493636b8151cc63cc863d9df1714e0b7d904357f29e26a", "task_id": "emo_Contentment-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.054614543914795, "target_z": 3.3750000147885015, "ce": 6.3641486167907715, "genuineness": 3.9801597595214844, "identity": 0.6631751656532288, "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_Contentment/de/ea51c0fb106975dccfb65706.mp3" }, { "key": "original-emo_Contentment-de-1-seed1702-scale1.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "ee946471b11ca5b643c022e472b98939d3e838b50b0274a2d394f8818bf1e623", "task_id": "emo_Contentment-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.991638422012329, "target_z": 3.2500000295770026, "ce": 6.332377910614014, "genuineness": 4.319066047668457, "identity": 0.48525679111480713, "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_Contentment/de/4899a047a4dcff2bbaedd9b1.mp3" }, { "key": "original-emo_Contentment-en-0-seed1701-scale0.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "a77b18bb15ef3cd8029eaff090a6ad20ceaa15334b965199d6701f39ada2d918", "task_id": "emo_Contentment-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.9601503610610962, "target_z": 3.1875000369712536, "ce": 6.062326908111572, "genuineness": 3.7416701316833496, "identity": 0.33846956491470337, "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_Contentment/en/387bd86a0cccb058929bda97.mp3" }, { "key": "original-emo_Contentment-en-0-seed1701-scale0.5", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "f34867dee9c502a3846cb01cb0e323fefe006d69d272319a057ca80836f1c148", "task_id": "emo_Contentment-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.259286880493164, "target_z": 3.781249848417861, "ce": 6.2767791748046875, "genuineness": 4.105680465698242, "identity": 0.3118313252925873, "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_Contentment/en/072167d7e83358082c23fa78.mp3" }, { "key": "original-emo_Contentment-en-0-seed1701-scale0.75", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "9f3ff2986b36288736afabe8643383125bdb3a7961294b15e0873786df6e36db", "task_id": "emo_Contentment-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0861027240753174, "target_z": 3.4375002440102724, "ce": 6.260893821716309, "genuineness": 3.9676074981689453, "identity": 0.118694007396698, "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_Contentment/en/3f48c1b58e3067d7ebec42ff.mp3" }, { "key": "original-emo_Contentment-en-0-seed1701-scale1.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "afe8fe2406b195dd5432e099d9e9a4c7730a5c8c5e88ff06c24dc56ef2c1e4f6", "task_id": "emo_Contentment-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.125462770462036, "target_z": 3.5156251756134536, "ce": 6.09409761428833, "genuineness": 3.7793264389038086, "identity": 0.5355165600776672, "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_Contentment/en/ec7512d01ea122f8628225c1.mp3" }, { "key": "original-emo_Contentment-en-0-seed1702-scale0.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "7cac99c6718ebbdbe00e57de6307759d47578f719b5637da465eeb90a8e2a324", "task_id": "emo_Contentment-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1963107585906982, "target_z": 3.6562498632063622, "ce": 6.268836498260498, "genuineness": 4.017816066741943, "identity": 0.31938037276268005, "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_Contentment/en/40a95b89907f581fd271dd49.mp3" }, { "key": "original-emo_Contentment-en-0-seed1702-scale0.5", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "6ebc052f5c89de9480ba01fd8dfede62106bb13f5b162566ffcc6034fc7819a6", "task_id": "emo_Contentment-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.164822816848755, "target_z": 3.5937501072166347, "ce": 6.308549880981445, "genuineness": 4.093128204345703, "identity": 0.20850372314453125, "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_Contentment/en/648d97d6f79e0178053261b1.mp3" }, { "key": "original-emo_Contentment-en-0-seed1702-scale0.75", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "82d5c7128600f9a62dee348258931dbf83eee81e9051e89f93f3934ea84a28f8", "task_id": "emo_Contentment-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1175906658172607, "target_z": 3.5, "ce": 6.221180438995361, "genuineness": 3.9927117824554443, "identity": 0.293967604637146, "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_Contentment/en/e526ec91582f606a490b8457.mp3" }, { "key": "original-emo_Contentment-en-0-seed1702-scale1.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "a378fbdd04db940fab65dc848490aa03b4e1bd134b9b65f52aae33cee61838f7", "task_id": "emo_Contentment-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1333346366882324, "target_z": 3.531249877994864, "ce": 6.23706579208374, "genuineness": 4.344170093536377, "identity": 0.26411324739456177, "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_Contentment/en/1e5ca7235434217b0d634850.mp3" }, { "key": "original-emo_Contentment-en-1-seed1701-scale0.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "fde95f2148bfdcead2df5cb41d521adcc0258694322b73ad0810b6d6f4c024b7", "task_id": "emo_Contentment-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.574167490005493, "target_z": 4.406249774475354, "ce": 6.427689552307129, "genuineness": 4.425758361816406, "identity": 0.3124702572822571, "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_Contentment/en/729e62e2d9bb43dc15e47885.mp3" }, { "key": "original-emo_Contentment-en-1-seed1701-scale0.5", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "0eaba6ba5917b93da76e3f9176b2e860f0d8c0f4cd6954179fefddd19821a5a4", "task_id": "emo_Contentment-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.259286880493164, "target_z": 3.781249848417861, "ce": 6.348263263702393, "genuineness": 4.545003414154053, "identity": 0.4706232249736786, "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_Contentment/en/0e46c42271ce576e322698b5.mp3" }, { "key": "original-emo_Contentment-en-1-seed1701-scale0.75", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "9d3e72ceb4c1142ccdf31cbfcd44c095df65706f3e30e64e576a6def383b0997", "task_id": "emo_Contentment-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4954473972320557, "target_z": 4.249999911268992, "ce": 6.340320587158203, "genuineness": 4.256305694580078, "identity": 0.32117050886154175, "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_Contentment/en/cde86bd3d829af9b4299d06b.mp3" }, { "key": "original-emo_Contentment-en-1-seed1701-scale1.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "28f95a6a42bad2ced4816d7f016e7e860ab416e7861482dd879abc5bb82df44a", "task_id": "emo_Contentment-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5111913681030273, "target_z": 4.281249789263856, "ce": 6.23706579208374, "genuineness": 4.281409740447998, "identity": 0.3929675221443176, "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_Contentment/en/9e75d37641c8e611b7575402.mp3" }, { "key": "original-emo_Contentment-en-1-seed1702-scale0.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "73fac936aa35a493bb0cc7760f0154a378b8eb8c0df34a7bdf6826f0a2744933", "task_id": "emo_Contentment-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.32226300239563, "target_z": 3.9062498336293596, "ce": 6.348263263702393, "genuineness": 4.369274139404297, "identity": 0.30911123752593994, "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_Contentment/en/e6f244c7128b3aa37d909e8f.mp3" }, { "key": "original-emo_Contentment-en-1-seed1702-scale0.5", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "7d402b3d49572a8ce10ea10572da8ae784969d3671a29e8f1b46aa95b44bd3b2", "task_id": "emo_Contentment-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5584235191345215, "target_z": 4.374999896480491, "ce": 6.38797664642334, "genuineness": 4.519899368286133, "identity": 0.33284205198287964, "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_Contentment/en/c55b28bf1f535411be20610f.mp3" }, { "key": "original-emo_Contentment-en-1-seed1702-scale0.75", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "6101eb10be23d7b9f8b781e3b2aba16722107454d3e8bf871a067924c3e1d33e", "task_id": "emo_Contentment-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.54267954826355, "target_z": 4.343750018485626, "ce": 6.24500846862793, "genuineness": 4.231201171875, "identity": 0.45426467061042786, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Contentment/en/0847f7be1bb4dcdffd4009ed.mp3" }, { "key": "original-emo_Contentment-en-1-seed1702-scale1.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "a6eb8fb93c5c93d8e0169c39db3aa8502dd4f0da50b0f36b65670a474988721f", "task_id": "emo_Contentment-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4009833335876465, "target_z": 4.062500170067765, "ce": 6.419747352600098, "genuineness": 4.557555198669434, "identity": 0.4540802240371704, "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_Contentment/en/9930668df28f96018259b929.mp3" }, { "key": "original-emo_Contentment-es-0-seed1701-scale0.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "76654ce21966273053416128f96c6e7f6d0a616981a1cf62db2abf55714a78df", "task_id": "emo_Contentment-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.2514150142669678, "target_z": 3.765625146036451, "ce": 6.133810997009277, "genuineness": 4.256305694580078, "identity": 0.5490193367004395, "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_Contentment/es/ed7ad83e7b16a1a95295d732.mp3" }, { "key": "original-emo_Contentment-es-0-seed1701-scale0.5", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "7ec0ac9b5716a84f36909192b7232a1a441a1ef51f65a0db13e1a7b99e8e90cd", "task_id": "emo_Contentment-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.4009833335876465, "target_z": 4.062500170067765, "ce": 6.09409761428833, "genuineness": 4.268857479095459, "identity": 0.6844205856323242, "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_Contentment/es/a4e11fe3eefbf96deb3a5929.mp3" }, { "key": "original-emo_Contentment-es-0-seed1701-scale0.75", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "21804782952a2de7a1e3d7f76aef9697e95557cb101f002a633aeffbe9ffe4c1", "task_id": "emo_Contentment-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.6925017833709717, "target_z": 2.656249981514373, "ce": 6.1020402908325195, "genuineness": 4.231201171875, "identity": 0.4317966103553772, "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_Contentment/es/057c852906362630d1a41c4a.mp3" }, { "key": "original-emo_Contentment-es-0-seed1701-scale1.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "be3a073351f2b773e6cd638438542b4bff7b7c8e82144d3b278c352d3abdf92d", "task_id": "emo_Contentment-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.1963107585906982, "target_z": 3.6562498632063622, "ce": 5.6334228515625, "genuineness": 3.9676074981689453, "identity": 0.4015032649040222, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Contentment/es/0153a2ea1e469311c50ef7ac.mp3" }, { "key": "original-emo_Contentment-es-0-seed1702-scale0.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "600a96563844d7108dfccd10e7b52ab58f1eebd1cbbc6f59a9fb9126117e8acb", "task_id": "emo_Contentment-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.141206741333008, "target_z": 3.5468750536083173, "ce": 6.070269584655762, "genuineness": 4.268857479095459, "identity": 0.7030224800109863, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Contentment/es/0473dd13d9f88cafea416983.mp3" }, { "key": "original-emo_Contentment-es-0-seed1702-scale0.5", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "d8eb0c4a0352e92d2ab9321a1fc4dec6f649d1d75b628ae415444434bcaeebd2", "task_id": "emo_Contentment-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.6452696323394775, "target_z": 2.5624998742977385, "ce": 5.935244083404541, "genuineness": 4.080576419830322, "identity": 0.5663047432899475, "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_Contentment/es/c16adfc92f48435d31273f08.mp3" }, { "key": "original-emo_Contentment-es-0-seed1702-scale0.75", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "75b600ce1de285ba47e930cb71519e1ba13bab4e125b857ac8cd89469fb167a1", "task_id": "emo_Contentment-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.4799573421478271, "target_z": 2.23437497227156, "ce": 6.157639026641846, "genuineness": 4.532451152801514, "identity": 0.4588046073913574, "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_Contentment/es/8a9d68cc93ae991c93ebb8c0.mp3" }, { "key": "original-emo_Contentment-es-0-seed1702-scale1.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 1.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "7ac270bbe168eeb30a4f52a24caaead506e85d6c35e36165d1828b695507a1db", "task_id": "emo_Contentment-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.054614543914795, "target_z": 3.3750000147885015, "ce": 5.895530700683594, "genuineness": 3.9048471450805664, "identity": 0.6057133078575134, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Contentment/es/e91c21994931b32121ecc90f.mp3" }, { "key": "original-emo_Contentment-es-1-seed1701-scale0.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "c59fbdfe048424db7b6cf289cd7208b3a88c1807c631c657dd2169ce7047f9c9", "task_id": "emo_Contentment-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.275031089782715, "target_z": 3.8125001996447683, "ce": 6.125868320465088, "genuineness": 4.18099308013916, "identity": 0.4756264090538025, "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_Contentment/es/a2e187076c2d206ac2d1434e.mp3" }, { "key": "original-emo_Contentment-es-1-seed1701-scale0.5", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "eb4b8fcce2a5be5bc2e7ed9d8c0857a000db04cbc9891ead98fa4d2bfb1a1276", "task_id": "emo_Contentment-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.2041828632354736, "target_z": 3.6718750388198163, "ce": 6.09409761428833, "genuineness": 4.65797233581543, "identity": 0.5998892784118652, "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_Contentment/es/9f7716c7beb1661f951156e0.mp3" }, { "key": "original-emo_Contentment-es-1-seed1701-scale0.75", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "a0e30571003dd1a9cf98541a7603e42c88c003972067e647c0a702047d9db988", "task_id": "emo_Contentment-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.149078845977783, "target_z": 3.562500229221771, "ce": 5.982900142669678, "genuineness": 4.425758361816406, "identity": 0.6968518495559692, "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_Contentment/es/c6d55ec66589895bdaaaf8ee.mp3" }, { "key": "original-emo_Contentment-es-1-seed1701-scale1.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "05a2263a9913b3f06951e46546e2b46cb4481e6cb6315116f81dad2d4b7e6739", "task_id": "emo_Contentment-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.212054967880249, "target_z": 3.68750021443327, "ce": 6.141753673553467, "genuineness": 4.507347106933594, "identity": 0.6894540786743164, "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_Contentment/es/6b9814f1dda3f6c83262977b.mp3" }, { "key": "original-emo_Contentment-es-1-seed1702-scale0.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "9d479ac55ab64d7c6e81240467fd900a77f5bfa5cf489bc223f8374efaf40fd0", "task_id": "emo_Contentment-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.3852391242980957, "target_z": 4.031249818840858, "ce": 6.181467056274414, "genuineness": 4.570107460021973, "identity": 0.5850569009780884, "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_Contentment/es/df71c8b45b80b4079b132679.mp3" }, { "key": "original-emo_Contentment-es-1-seed1702-scale0.5", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "905d20c0af7eec6b5866a99fd52b60c45238a3e631b99330f4594d661ec0f7ca", "task_id": "emo_Contentment-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.369495153427124, "target_z": 3.9999999408459948, "ce": 6.117925643920898, "genuineness": 4.570107460021973, "identity": 0.669152021408081, "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_Contentment/es/92a1c27596b1c34b2de376e7.mp3" }, { "key": "original-emo_Contentment-es-1-seed1702-scale0.75", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "e9352249035af10f88d73084b33f979f4407d5113eed6f77129d6db408db610f", "task_id": "emo_Contentment-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.141206741333008, "target_z": 3.5468750536083173, "ce": 6.0146708488464355, "genuineness": 4.7458367347717285, "identity": 0.5637532472610474, "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_Contentment/es/45e75a290c249a7f36ed5d32.mp3" }, { "key": "original-emo_Contentment-es-1-seed1702-scale1.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "98d4a4c6a2459c7156493fb701be3874632b3824b8fc1ae15e22edef649a19d3", "task_id": "emo_Contentment-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.188438892364502, "target_z": 3.6406251608249525, "ce": 6.0146708488464355, "genuineness": 4.306513786315918, "identity": 0.6308570504188538, "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_Contentment/es/246126898764385c4d245c05.mp3" }, { "key": "original-emo_Contentment-fr-0-seed1701-scale0.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "3adcb84cc46c7c5bcee429ad521b81ee58f235d528ccf6f68878a1ece1e0b159", "task_id": "emo_Contentment-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.2907750606536865, "target_z": 3.843750077639632, "ce": 6.181467056274414, "genuineness": 4.406930446624756, "identity": 0.5958658456802368, "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_Contentment/fr/56feacb2f434a5badfcdd0f7.mp3" }, { "key": "original-emo_Contentment-fr-0-seed1701-scale0.5", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "c58242b80fff3936969ac10c43ce91e4a71c3fe281dfd39f9816fb507f2abf2d", "task_id": "emo_Contentment-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.8105820417404175, "target_z": 2.890625012939939, "ce": 6.086154937744141, "genuineness": 4.394378662109375, "identity": 0.7100000381469727, "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_Contentment/fr/e517dbc2daf15380e9109f9f.mp3" }, { "key": "original-emo_Contentment-fr-0-seed1701-scale0.75", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "2f5beccbd8b8982d76b6f65be7a22d19d0403485632fd4b5157c08aa35b7ecf5", "task_id": "emo_Contentment-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.7161178588867188, "target_z": 2.7031250351226905, "ce": 6.1894097328186035, "genuineness": 4.557555198669434, "identity": 0.764359712600708, "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_Contentment/fr/a4a5a7e8f77a7b9d050fe857.mp3" }, { "key": "original-emo_Contentment-fr-0-seed1701-scale1.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "646b766a376cd932d67132faee8c46b2c2460cd860f8b1146f9e183eef290e52", "task_id": "emo_Contentment-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.3343250751495361, "target_z": 1.945312536046972, "ce": 6.054384231567383, "genuineness": 4.595211505889893, "identity": 0.7833070755004883, "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_Contentment/fr/4fdc791800893b94a00153d4.mp3" }, { "key": "original-emo_Contentment-fr-0-seed1702-scale0.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "93b8ae2964377c16b796f51751459e0c7eb44a341388802475a5b45d96b884ef", "task_id": "emo_Contentment-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.5035734176635742, "target_z": 2.2812500258798774, "ce": 6.062326908111572, "genuineness": 4.432034492492676, "identity": 0.812620222568512, "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_Contentment/fr/ce48ab2f7aa9f1338fd09aa9.mp3" }, { "key": "original-emo_Contentment-fr-0-seed1702-scale0.5", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "94721923f223b05563eaad5acf82b47a046dcdbd3c116fdb5143306134985fff", "task_id": "emo_Contentment-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.0231266021728516, "target_z": 3.312500258798774, "ce": 6.1020402908325195, "genuineness": 4.042920112609863, "identity": 0.7245328426361084, "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_Contentment/fr/cd4d130b50428effb6daa4fd.mp3" }, { "key": "original-emo_Contentment-fr-0-seed1702-scale0.75", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "2244a226fdb2425f4761f9889607f0e56789b8639322b27be9646c1f3d450e50", "task_id": "emo_Contentment-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.030998468399048, "target_z": 3.3281249611801837, "ce": 6.173524379730225, "genuineness": 4.406930446624756, "identity": 0.7180806398391724, "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_Contentment/fr/aa7dc277004300a0add95104.mp3" }, { "key": "original-emo_Contentment-fr-0-seed1702-scale1.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "01336e6ab6213bb9c7ae34c97a4623e84dd2dbce4a7faf03e3ba4e3816ca251f", "task_id": "emo_Contentment-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.164822816848755, "target_z": 3.5937501072166347, "ce": 6.086154937744141, "genuineness": 4.2249250411987305, "identity": 0.7690517902374268, "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_Contentment/fr/51da903806395bb62849c8d7.mp3" }, { "key": "original-emo_Contentment-fr-1-seed1701-scale0.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "4d83d1af1907ead7af7f51d9dda3b5844ad8d653b91c61f9a29c00f6edca1240", "task_id": "emo_Contentment-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.3852391242980957, "target_z": 4.031249818840858, "ce": 6.181467056274414, "genuineness": 4.325342178344727, "identity": 0.745569109916687, "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_Contentment/fr/5349e372d047970baa516799.mp3" }, { "key": "original-emo_Contentment-fr-1-seed1701-scale0.5", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "fde05b9fc2826d2b5ed3fd71a81a51333a5f90c48fa3bdcd14eab910314c06ea", "task_id": "emo_Contentment-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.3852391242980957, "target_z": 4.031249818840858, "ce": 6.109982967376709, "genuineness": 4.557555198669434, "identity": 0.6677500009536743, "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_Contentment/fr/76e730e3c1d4f912c21a3d52.mp3" }, { "key": "original-emo_Contentment-fr-1-seed1701-scale0.75", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "36fba6fa9d0a7da2dddf940c37805ab96c7c7a552c289bbfb4e6b527a8707f04", "task_id": "emo_Contentment-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.282902956008911, "target_z": 3.8281249020261785, "ce": 6.1894097328186035, "genuineness": 4.758388519287109, "identity": 0.687903642654419, "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_Contentment/fr/6a51e63e637edee6a65f34da.mp3" }, { "key": "original-emo_Contentment-fr-1-seed1701-scale1.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "5ef79902544c5c08e90e542817507a15529960e5624013e9ce7661078b5392b0", "task_id": "emo_Contentment-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.526935577392578, "target_z": 4.312500140490763, "ce": 6.117925643920898, "genuineness": 4.595211505889893, "identity": 0.7466936707496643, "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_Contentment/fr/e342cc240539b236fa0a1d05.mp3" }, { "key": "original-emo_Contentment-fr-1-seed1702-scale0.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "9643000f80263ac7f41aba1b815a9fe69c78129269aa3fe3bce55aec031c8b0d", "task_id": "emo_Contentment-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.4639594554901123, "target_z": 4.187500155279264, "ce": 6.260893821716309, "genuineness": 4.545003414154053, "identity": 0.693568229675293, "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_Contentment/fr/609b01daafab25186e219127.mp3" }, { "key": "original-emo_Contentment-fr-1-seed1702-scale0.5", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "194dcabf29cfa784391b3ca89bdd99ff85e63e7547dabdec1ef85d6d9a7bedee", "task_id": "emo_Contentment-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.4009833335876465, "target_z": 4.062500170067765, "ce": 6.046441555023193, "genuineness": 4.883909225463867, "identity": 0.5372560024261475, "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_Contentment/fr/0b3ef80f21ccd9bc24577b0b.mp3" }, { "key": "original-emo_Contentment-fr-1-seed1702-scale0.75", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "1827c2d4b6f9b9a5510b74ebc9d15b443cc69b108aae935f59ebe27a3861215d", "task_id": "emo_Contentment-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.1805667877197266, "target_z": 3.6249999852114985, "ce": 6.070269584655762, "genuineness": 4.883909225463867, "identity": 0.7007299065589905, "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_Contentment/fr/6cc69ef1d234f92b01320823.mp3" }, { "key": "original-emo_Contentment-fr-1-seed1702-scale1.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "7803139755f8b38e23a871dcaf097e4756d53b034c8a7ee6bda27429d690caaf", "task_id": "emo_Contentment-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 2.1097185611724854, "target_z": 3.4843748243865464, "ce": 6.062326908111572, "genuineness": 4.632867813110352, "identity": 0.6772669553756714, "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_Contentment/fr/f7580d7d787fd83546a38f31.mp3" }, { "key": "original-emo_Contentment-nl-0-seed1701-scale0.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "8d38a446e4fd50cc2b5d7ef93640c85672c23082ceb94ef974ab7a0ce14ff197", "task_id": "emo_Contentment-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.712435781955719, "target_z": 0.7109375046214067, "ce": 6.09409761428833, "genuineness": 4.344170093536377, "identity": 0.6291823387145996, "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_Contentment/nl/c82b6c822adcb14527e5c386.mp3" }, { "key": "original-emo_Contentment-nl-0-seed1701-scale0.5", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "bff05afc2df633d623f5dca1f25264f35d63f9ec7f2cc0e16ceb9fab150ad5f5", "task_id": "emo_Contentment-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6081315279006958, "target_z": 0.5039061755953526, "ce": 6.038498878479004, "genuineness": 4.143336772918701, "identity": 0.7399090528488159, "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_Contentment/nl/adc5222e206fb3642dec0bad.mp3" }, { "key": "original-emo_Contentment-nl-0-seed1701-scale0.75", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "d5f967407131635ab7bae0d9c8a748fde597e4ef175f24e2ef352b187ea5fbe4", "task_id": "emo_Contentment-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0037003755569458, "target_z": 1.2890624953785934, "ce": 6.23706579208374, "genuineness": 4.356721878051758, "identity": 0.5647100210189819, "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_Contentment/nl/f240fc9c2a85eb1f9ed3ac20.mp3" }, { "key": "original-emo_Contentment-nl-0-seed1701-scale1.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "11ca656367cdaf60cd1e36407e927b77f87d8c8cc7866bcc741dcd9a7ea4cf41", "task_id": "emo_Contentment-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6730756759643555, "target_z": 0.6328124547102146, "ce": 6.109982967376709, "genuineness": 4.218649387359619, "identity": 0.8209092617034912, "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_Contentment/nl/86166bb487dad2822b0832b2.mp3" }, { "key": "original-emo_Contentment-nl-0-seed1702-scale0.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "930da9cb5fed6980399119367d373ab9996fa3404e1feebbe6edb289899a82a4", "task_id": "emo_Contentment-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0745484828948975, "target_z": 1.4296874195875238, "ce": 6.046441555023193, "genuineness": 4.344170093536377, "identity": 0.5271144509315491, "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_Contentment/nl/89f739d46b8a2107df44dfc4.mp3" }, { "key": "original-emo_Contentment-nl-0-seed1702-scale0.5", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "fb13d75d542c1085a76f0e85e8f6f78f1ecd04b947f1df4e32b35d6052ba918f", "task_id": "emo_Contentment-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6888197660446167, "target_z": 0.6640625693211001, "ce": 5.919358730316162, "genuineness": 4.124508857727051, "identity": 0.6745400428771973, "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_Contentment/nl/4fe5cf5e9af8081c91c3bd02.mp3" }, { "key": "original-emo_Contentment-nl-0-seed1702-scale0.75", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "73266493fe8cf1877f9ab1ce70ab3066df87b680dbfaee34a094158000309dd9", "task_id": "emo_Contentment-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7714759111404419, "target_z": 0.8281250203341893, "ce": 5.816103935241699, "genuineness": 4.406930446624756, "identity": 0.5606982707977295, "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_Contentment/nl/bd7327f108d9070f3b413772.mp3" }, { "key": "original-emo_Contentment-nl-0-seed1702-scale1.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "05167e88d2c72e9c32f68f45462ff3778e77af393afc87ddb15726b6f09f5682", "task_id": "emo_Contentment-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8029639720916748, "target_z": 0.8906250129399387, "ce": 6.181467056274414, "genuineness": 4.18726921081543, "identity": 0.5787405967712402, "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_Contentment/nl/ec342dad8c7f188f7c22f2c7.mp3" }, { "key": "original-emo_Contentment-nl-1-seed1701-scale0.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "15f8e6f158ade7a63e822f3c82424422ff8e63ce49d5c52e5d36a4eb585d2fcb", "task_id": "emo_Contentment-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.8184540271759033, "target_z": 2.9062499519373706, "ce": 6.086154937744141, "genuineness": 4.218649387359619, "identity": 0.7477277517318726, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Contentment/nl/209fce78082ab779c092556d.mp3" }, { "key": "original-emo_Contentment-nl-1-seed1701-scale0.5", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "340ae890d8bb4deb5366a4a016db1f67180651f7acf311fabcce7475aefcc1bf", "task_id": "emo_Contentment-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.857814073562622, "target_z": 2.9843748835405517, "ce": 6.109982967376709, "genuineness": 4.444586753845215, "identity": 0.711498498916626, "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_Contentment/nl/71b40c586769326f4949495d.mp3" }, { "key": "original-emo_Contentment-nl-1-seed1701-scale0.75", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "3c07f735ed7d02226538c850fe01792dc24a7bfc41ba90c2a7853d5e41a27ca5", "task_id": "emo_Contentment-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.3697490692138672, "target_z": 2.0156248798434264, "ce": 6.062326908111572, "genuineness": 4.325342178344727, "identity": 0.513933002948761, "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_Contentment/nl/5c20dc4ccfe231cb46f5e3bd.mp3" }, { "key": "original-emo_Contentment-nl-1-seed1701-scale1.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "0bef0a5e5045534b109a22965facfb3d0be2f7983a8abb585c6eccb3f1ae38c9", "task_id": "emo_Contentment-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.3697490692138672, "target_z": 2.0156248798434264, "ce": 6.197352409362793, "genuineness": 4.20609712600708, "identity": 0.7529903650283813, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Contentment/nl/f02678dba7843c75caa08ab2.mp3" }, { "key": "original-emo_Contentment-nl-1-seed1702-scale0.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "ace62b02dc3120911f7da0cd3960c024c039ba07c38834b5ac35bc012d764bbd", "task_id": "emo_Contentment-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.7948379516601562, "target_z": 2.8593748983290532, "ce": 6.197352409362793, "genuineness": 4.250029563903809, "identity": 0.6579959392547607, "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_Contentment/nl/1752dfc3ae6c5539d6a6e1df.mp3" }, { "key": "original-emo_Contentment-nl-1-seed1702-scale0.5", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "e1f55aaf3686dfd4ad07edc2e76ada26dfdd63d209f50f735b49b86d80eee1c6", "task_id": "emo_Contentment-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.598037600517273, "target_z": 2.4687500036971253, "ce": 6.133810997009277, "genuineness": 4.394378662109375, "identity": 0.6575928926467896, "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_Contentment/nl/6e6dd43db3f8e953c06fc392.mp3" }, { "key": "original-emo_Contentment-nl-1-seed1702-scale0.75", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "ecd0fc545cf4b129a36c136deecee2803159b1f19cc2fad60c012fe0a874efef", "task_id": "emo_Contentment-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.3579410314559937, "target_z": 1.9921873530392677, "ce": 6.1894097328186035, "genuineness": 4.281409740447998, "identity": 0.8006572723388672, "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_Contentment/nl/b2e288fc96babff456989c05.mp3" }, { "key": "original-emo_Contentment-nl-1-seed1702-scale1.0", "bucket": "emo_Contentment", "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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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 Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Contentment. 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": "b42bc21c015039edd87948b919a086f99762ea73ead303d20ed597ef11e5f425", "mp3_sha256": "d56134e36b76479a896ac9826242b0626420d95a60702de4999de8cf34c57d7f", "task_id": "emo_Contentment-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Contentment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Contentment. 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 Contentment. 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 Contentment. 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": 1.6137815713882446, "target_z": 2.499999881691989, "ce": 6.038498878479004, "genuineness": 4.369274139404297, "identity": 0.5380369424819946, "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_Contentment/nl/54a825381850562796409df6.mp3" } ], "source_standard_audio_unchanged": true }