{ "complete": true, "report": { "bucket": "emo_Disgust", "label": "Intense Disgust", "definition": { "id": "emo_Disgust", "category": "emotion", "head": "emo_Disgust", "pole": "high", "label": "Intense Disgust", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_disgust/full-v2-sealed/sealed-selected", "mission": "emotion_disgust", "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": 6.327810764312744, "genuineness": 4.145345120429993, "wer": 0.007873211162421396, "identity": 0.6385920643806458, "voiceclap": 0.1030742752738297, "fitness": 0.5667723670039997, "steering_v2": 0.48078939572491985, "raw_target": 0.23461516156792642, "target_cdf": 0.48078939572491985, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 0.99, "by_arm": { "reference": { "n": 50, "ce": 6.337143421173096, "genuineness": 4.1153456449508665, "wer": 0.007337820174305157, "identity": 0.6385920643806458, "fitness": 0.5806094079856661, "steering_v2": 0.5093039358037883 }, "none": { "n": 50, "ce": 6.318478107452393, "genuineness": 4.175344595909118, "wer": 0.008408602150537634, "identity": null, "fitness": 0.5529353260223333, "steering_v2": 0.4522748556460514 } } } } ], "selected_wording": { "id": "manual-981ced9f650c", "general": "A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.", "inline": [ "A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.", "A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.", "A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable." ], "cfg": 3, "recipe": "P06", "strategy": "initial-physical-directing", "timing_syntax": "canonical", "canonical_labels": true, "neutral_event": "keep", "parent": "cfg-3", "origin": "exact_frozen_manual_recipe" }, "selection": { "manual_no_adapter": { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 0.2983886898500784, "target_raw": 0.36876909956336024, "ce": 6.112365865707398, "genuineness": 4.000399971008301, "identity": 0.5791623383760452, "wer": 0.005756578947368421, "valid_fraction": 1, "identity_delta": 0.01883490979671478, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 1.0583984269571536, "target_raw": 0.7413789968937635, "ce": 6.016656613349914, "genuineness": 3.849618124961853, "identity": 0.5483303263783454, "wer": 0.009089912280701754, "valid_fraction": 1, "identity_delta": -0.011997102200984955, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 0.2983886898500784, "target_raw": 0.36876909956336024, "ce": 6.112365865707398, "genuineness": 4.000399971008301, "identity": 0.5791623383760452, "wer": 0.005756578947368421, "valid_fraction": 1, "identity_delta": 0.01883490979671478, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": -0.059960925437463924, "target_raw": 0.1930810697376728, "ce": 6.1957638502120975, "genuineness": 4.248774230480194, "identity": 0.6122278824448586, "wer": 0.003125, "valid_fraction": 1, "identity_delta": 0.05190045386552811, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": -0.20537109360752911, "target_raw": 0.12179084122180939, "ce": 6.216414833068848, "genuineness": 4.348877084255219, "identity": 0.6061655938625335, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.04583816528320313, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": -0.32656249316139685, "target_raw": 0.06237434595823288, "ce": 6.207082223892212, "genuineness": 4.335069811344146, "identity": 0.6170286029577255, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.05670117437839508, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": -0.3551757815824321, "target_raw": 0.04834611192345619, "ce": 6.182062745094299, "genuineness": 4.239046359062195, "identity": 0.5387595556676388, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.021567872911691665, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": -0.38002930022306614, "target_raw": 0.03616117984056473, "ce": 6.254539656639099, "genuineness": 4.364880990982056, "identity": 0.5774336978793144, "wer": 0.01111111111111111, "valid_fraction": 0.95, "identity_delta": 0.01710626929998398, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": -0.3987792956639974, "target_raw": 0.026968621462583543, "ce": 6.18424699306488, "genuineness": 4.313103687763214, "identity": 0.5696872487664223, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.009359820187091828, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 0.955908239288863, "target_raw": 0.691131142899394, "ce": 5.955349135398865, "genuineness": 3.8538544893264772, "identity": 0.5072811588644981, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.053046269714832305, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 1.0583984269571536, "target_raw": 0.7413789968937635, "ce": 6.016656613349914, "genuineness": 3.849618124961853, "identity": 0.5483303263783454, "wer": 0.009089912280701754, "valid_fraction": 1, "identity_delta": -0.011997102200984955, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 0.9689941502892759, "target_raw": 0.6975467711687088, "ce": 5.9769432067871096, "genuineness": 3.8190224051475523, "identity": 0.5350859887897969, "wer": 0.01513888888888889, "valid_fraction": 1, "identity_delta": -0.025241439789533617, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 0.32709961908676627, "target_raw": 0.3828452039510012, "ce": 6.062326979637146, "genuineness": 4.066769051551819, "identity": 0.5395795553922653, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.020747873187065124, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 0.3232421811362999, "target_raw": 0.3809540182352066, "ce": 6.105614542961121, "genuineness": 4.112270414829254, "identity": 0.5862620234489441, "wer": 0.005756578947368421, "valid_fraction": 1, "identity_delta": 0.025934594869613647, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 0.1696289162704532, "target_raw": 0.30564205832779406, "ce": 6.1568447828292845, "genuineness": 4.084028208255768, "identity": 0.528902217745781, "wer": 0.031578947368421054, "valid_fraction": 0.95, "identity_delta": -0.0314252108335495, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": -0.011230460439197568, "target_raw": 0.21697214990854263, "ce": 6.190204000473022, "genuineness": 4.198565948009491, "identity": 0.58334781229496, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.02302038371562958, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": -0.18349609968628744, "target_raw": 0.1325154922902584, "ce": 6.19973521232605, "genuineness": 4.248146569728851, "identity": 0.6034207090735435, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.043093280494213106, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": -0.1988769577553042, "target_raw": 0.12497472055256367, "ce": 6.146320748329162, "genuineness": 4.236222195625305, "identity": 0.5457484364509583, "wer": 0.0125, "valid_fraction": 0.95, "identity_delta": -0.014578992128372192, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": -0.2710937534193016, "target_raw": 0.0895689994096756, "ce": 6.205295085906982, "genuineness": 4.293334126472473, "identity": 0.5727880373597145, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.012460608780384064, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": -0.2723632808225873, "target_raw": 0.08894658833742142, "ce": 6.190998291969299, "genuineness": 4.303375828266144, "identity": 0.5318611837923527, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.02846624478697777, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": -0.27968749772046564, "target_raw": 0.08535574525594711, "ce": 6.194572472572327, "genuineness": 4.322517776489258, "identity": 0.610982483625412, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.050655055046081546, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": -0.281445312025097, "target_raw": 0.08449394181370735, "ce": 6.187026953697204, "genuineness": 4.318438339233398, "identity": 0.5738200321793556, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.013492603600025178, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": -0.33369141019169485, "target_raw": 0.05887925252318382, "ce": 6.207677841186523, "genuineness": 4.335383582115173, "identity": 0.5606590911746026, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0003316625952720642, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": -0.34619140867200526, "target_raw": 0.05275087952613831, "ce": 6.2160176753997805, "genuineness": 4.381512546539307, "identity": 0.5882888481020927, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0279614195227623, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": -0.3668945327221993, "target_raw": 0.04260076098144054, "ce": 6.211649179458618, "genuineness": 4.367077624797821, "identity": 0.5574537843465805, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.002873644232749939, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": -0.36787109664690826, "target_raw": 0.04212198108434677, "ce": 6.203706526756287, "genuineness": 4.337893998622894, "identity": 0.5696823313832283, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.009354902803897858, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": -0.38486328538165604, "target_raw": 0.033791222423315045, "ce": 6.228725934028626, "genuineness": 4.382767629623413, "identity": 0.554039117693901, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.006288310885429383, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": -0.3928710920878395, "target_raw": 0.029865235835313798, "ce": 6.199735164642334, "genuineness": 4.36958794593811, "identity": 0.5772968694567681, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.01696944087743759, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": -0.393505857309172, "target_raw": 0.029554029554128648, "ce": 6.231505870819092, "genuineness": 4.436114048957824, "identity": 0.5636866562068462, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.003359227627515793, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": -0.3967773394283827, "target_raw": 0.027950120344758033, "ce": 6.201323771476746, "genuineness": 4.329735159873962, "identity": 0.603515800088644, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.04318837150931358, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": -0.40292968721505823, "target_raw": 0.02493380941450596, "ce": 6.214826273918152, "genuineness": 4.3008654594421385, "identity": 0.5951018318533897, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0347744032740593, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": -0.4175781232903492, "target_raw": 0.01775212213397026, "ce": 6.228725957870483, "genuineness": 4.34385621547699, "identity": 0.5916718319058418, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.03134440332651138, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": -0.4192871122481631, "target_raw": 0.016914256289601325, "ce": 6.205096507072449, "genuineness": 4.292392730712891, "identity": 0.5613403737545013, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0010129451751708985, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 0.8585937625374391, "target_raw": 0.6434207841753959, "ce": 5.970886969566346, "genuineness": 3.863268494606018, "identity": 0.4564751386642456, "wer": 0.011312134502923977, "valid_fraction": 1, "identity_delta": -0.10385228991508484, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": -0.42231445319623545, "target_raw": 0.015430042147636413, "ce": 6.182658433914185, "genuineness": 4.419482564926147, "identity": 0.5603274285793305, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.5, "n": 20, "target_z": -0.42548827550367374, "target_raw": 0.013874012604355812, "ce": 6.172730088233948, "genuineness": 4.376491677761078, "identity": 0.5830547869205475, "wer": 0.003125, "valid_fraction": 1, "identity_delta": 0.02272735834121704, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": -0.4062500015196896, "target_raw": 0.02330595925450325, "ce": 6.196955275535584, "genuineness": 4.391083455085754, "identity": 0.6192057475447654, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.05887831896543503, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": -0.4157226567723933, "target_raw": 0.018661801517009736, "ce": 6.205692219734192, "genuineness": 4.363155102729797, "identity": 0.5614222943782806, "wer": 0.003125, "valid_fraction": 1, "identity_delta": 0.0010948657989501953, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": -0.35927734170791714, "target_raw": 0.046335240453481676, "ce": 6.244690752029419, "genuineness": 4.392244520187378, "identity": 0.5791316756606102, "wer": 0.006453980801806888, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": 0.25701172951130186, "target_raw": 0.3484832213819027, "ce": 6.160974950790405, "genuineness": 4.07178994178772, "identity": 0.5725966927409172, "wer": 0.014838915470494417, "valid_fraction": 0.98, "identity_delta": -0.006534982919692994, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": 1.0770703360361924, "target_raw": 0.7505332718789578, "ce": 5.973746328353882, "genuineness": 3.8139074563980104, "identity": 0.5145791156589985, "wer": 0.030860813099943533, "valid_fraction": 0.98, "identity_delta": -0.0645525600016117, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": 0.9040429842983241, "target_raw": 0.665703169554472, "ce": 6.035282201766968, "genuineness": 3.863425402641296, "identity": 0.5393581134080887, "wer": 0.021000941087897608, "valid_fraction": 1, "identity_delta": -0.039773562252521516, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": 0.1730273517378684, "ci95_z": [ -0.027070313544786572, 0.44271486678279526 ], "language_deltas": { "en": -0.04375000455906875, "de": -0.030273426197308707, "fr": 0.6654297214080739, "nl": 0.26103517424882355, "es": 0.012695293788822042 }, "languages_improved": 3, "clear_gain": false, "delta_ce": -0.06153587341308594, "delta_genuineness": -0.049517946243286134, "delta_wer": 0.009859872012045927, "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": 0.8200586065248906, "ci95_z": [ 0.3551953068581524, 1.2849219061916286 ], "language_deltas": { "en": 0.09433594671311811, "de": 0.36582029074944283, "fr": 1.4298828477378023, "nl": 1.3545898880584495, "es": 0.8556640593656402 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.18722862243652344, "delta_genuineness": -0.2578824853897095, "delta_wer": 0.016021897629449115, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 0.6162890712192189, "ci95_z": [ 0.4183203162802278, 0.7791015768420705 ], "language_deltas": { "en": 0.2392578021471147, "de": 0.5376953257023033, "fr": 0.8617187807737141, "nl": 0.7292968751899612, "es": 0.7134765722830017 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.08371580123901368, "delta_genuineness": -0.3204545783996582, "delta_wer": 0.008384934668687529, "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": 1793023382.2873876, "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. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "language": "es", "seed": 1701, "scale": 0.0, "cfg": 4.0, "frames": 128, "reference": true } }, "rows": [ { "id": "emo_Disgust-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_Disgust-es-1", "key": "0000db05322b8aed843e5010bc2310a8d122b19e89698d4fff521bb987ae4645", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2d7eeb3daed13c25c3c9df817acc4260249117e3097f432717020038f1aeda0a", "generation_seconds_batch": 18.772001510020345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.049468472599983215, "target_z": -0.5546874886023281, "ce": 6.109982967376709, "genuineness": 4.570107460021973, "identity": 0.6741765737533569, "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_Disgust/0000db05322b8aed843e5010bc2310a8d122b19e89698d4fff521bb987ae4645.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "003488a794cc5ca8eb1c28d19033e1fc18297ef2ec2343ed81eab780c287e699", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9a4559c175c4239a1bfa720312700b3d1ed4e089a15673d1818cf7d137b68032", "generation_seconds_batch": 18.993471857043914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20141181349754333, "target_z": -0.04296876709650783, "ce": 6.165581703186035, "genuineness": 4.2751336097717285, "identity": 0.5829381942749023, "hypothesis": "Die Tür 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_Disgust/003488a794cc5ca8eb1c28d19033e1fc18297ef2ec2343ed81eab780c287e699.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "0088bcdb53dd5e26da7cce74b945d626f423d6b31de34ea3f317c08e334ecf86", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b2b984fcc878cef6e7d9880fd946c9ca14b3424051907297d512d22e5ce7500e", "generation_seconds_batch": 18.944341050926596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004154786467552185, "target_z": -0.44531251139767186, "ce": 6.300607204437256, "genuineness": 4.262581825256348, "identity": 0.5964146852493286, "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_Disgust/0088bcdb53dd5e26da7cce74b945d626f423d6b31de34ea3f317c08e334ecf86.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "00902bffedc3da86bb208f9052f362c8a62449bb824ca74452b1f96e638d0048", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b76f7934da729e236a23a13dfd9cd7927826bccad9287e526049ace50bc058c9", "generation_seconds_batch": 19.688597412081435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009900137782096863, "target_z": -0.4335937594980599, "ce": 6.109982967376709, "genuineness": 4.607763767242432, "identity": 0.7164154052734375, "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_Disgust/00902bffedc3da86bb208f9052f362c8a62449bb824ca74452b1f96e638d0048.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "00b5990744efb648181cb858ea3f720abe80ef32bdfc2923f5a72223b737cae6", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a7260117ebf622a1cf44f0a2fd27f137e2a21ed91cfbf012db05b4fdb42cc572", "generation_seconds_batch": 14.581261145998724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11618912220001221, "target_z": -0.21679687974902995, "ce": 6.141753673553467, "genuineness": 4.143336772918701, "identity": 0.7404738664627075, "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_Disgust/00b5990744efb648181cb858ea3f720abe80ef32bdfc2923f5a72223b737cae6.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "01a5eda7c9d5367d464500ce9a11e2a6af93de82fb1876d3ca881be065f984b7", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7bcebe7f99be8c9edb9b07a9e81d7bfc5abfed3c979790056d1dd7e1ff130486", "generation_seconds_batch": 18.925945125054568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02809375524520874, "target_z": -0.3964843683513581, "ce": 5.959072113037109, "genuineness": 4.469690799713135, "identity": 0.5848898887634277, "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_Disgust/01a5eda7c9d5367d464500ce9a11e2a6af93de82fb1876d3ca881be065f984b7.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "6f42dbca52af5beccbde79a61afa3e4d718a0ed072283eac6203d8c03e7a5a30", "generation_seconds_batch": 15.35950863105245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027136191725730896, "target_z": -0.39843750379922394, "ce": 6.0146708488464355, "genuineness": 4.7081804275512695, "identity": 0.7557730674743652, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis-le bien et vérifie les deux derniers chiffres. Appelle-moi quand you're a 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_Disgust/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "02d6b4ab8676d83d5ab92561a4f0da535bf1e503b05677ea918a92e5802ca430", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "06c19b543dce814461e0246b8dc7d22a50ebd3c3a409de94a12d5db415abe3c1", "generation_seconds_batch": 18.99888477602508, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03797776997089386, "target_z": -0.5312499848031041, "ce": 6.23706579208374, "genuineness": 4.306513786315918, "identity": 0.7055451273918152, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/02d6b4ab8676d83d5ab92561a4f0da535bf1e503b05677ea918a92e5802ca430.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "037c3f2a487ff4e0c44817b24bcd4e97aa159cb7828559cec38d6be421fe468c", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "415d9b87a6a9589816b44d9282e7d14e12a5567279839e1612a2b1e3d3364032", "generation_seconds_batch": 18.84440712898504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0893774926662445, "target_z": -0.2714843683513581, "ce": 6.284721851348877, "genuineness": 4.582659721374512, "identity": 0.5214349031448364, "hypothesis": "Die Tür 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_Disgust/037c3f2a487ff4e0c44817b24bcd4e97aa159cb7828559cec38d6be421fe468c.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "0398ca88c38a5d5eb648434318b7518e3792ad23a4642d947aec2a9f06c90bde", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d3e5296df211e9f9eb76e5d2d51a5286453bca2cc83478aae7d4fe00d94ae4dd", "generation_seconds_batch": 18.8531412279699, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15066123008728027, "target_z": -0.14648436835135806, "ce": 5.967014789581299, "genuineness": 4.356721878051758, "identity": 0.716209352016449, "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_Disgust/0398ca88c38a5d5eb648434318b7518e3792ad23a4642d947aec2a9f06c90bde.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "03a3f827cb18861810cd92fc5149fd4cee4a71d6ff8b655cd2d7fa7afe5db862", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "20f2c0689fd4c11f7233a485987bacd0a6b4383dbd9b25f3d40ab001ba2b4d5c", "generation_seconds_batch": 21.063440139987506, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.10692198574542999, "target_z": -0.6718750075984479, "ce": 6.475345611572266, "genuineness": 4.457139015197754, "identity": 0.5141916275024414, "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_Disgust/03a3f827cb18861810cd92fc5149fd4cee4a71d6ff8b655cd2d7fa7afe5db862.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "046ca4c4a68fc7074ef292ed05677acf3569ba1f8145c6b731ee7947396e50f9", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ab539cc9f2e14917e42fa79cc934b5b07c7c2abaf5e9bd4b3a515754d48fe29b", "generation_seconds_batch": 18.711959389038384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10421964526176453, "target_z": -0.241210936075291, "ce": 6.181467056274414, "genuineness": 4.293961524963379, "identity": 0.63081955909729, "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_Disgust/046ca4c4a68fc7074ef292ed05677acf3569ba1f8145c6b731ee7947396e50f9.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": "0483cc20edadadce770f3ea664fdb9f20cb3834be4419c34c13c4c69b410246f", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ab80a290976a2c659f49f911ea2ed54bec89a67465a26529ab775fd94b61d2b9", "generation_seconds_batch": 19.361065022065304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9042596817016602, "target_z": 1.3906249924015521, "ce": 5.569881439208984, "genuineness": 3.9425034523010254, "identity": 0.6203501224517822, "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_Disgust/0483cc20edadadce770f3ea664fdb9f20cb3834be4419c34c13c4c69b410246f.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "048ea4cf9213da933a3495695800964c0acfc929dac859a3ad3d9acf4b30fa25", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "58cb4ef23e0bbb2dae686f27e429564f0ac34196c9636282eabfde5728c3890a", "generation_seconds_batch": 19.688597412081435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00733591616153717, "target_z": -0.46875001519689585, "ce": 6.24500846862793, "genuineness": 4.331617832183838, "identity": 0.745577335357666, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/048ea4cf9213da933a3495695800964c0acfc929dac859a3ad3d9acf4b30fa25.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "0588418b012a8bdb1db0120ab91b5327e999484d117da1b0ff5e3902a3153136", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bcc5e558918ecc87fc92a0f4990a96f9ed1b96e430300b497b5e6bdf8c1aaec8", "generation_seconds_batch": 18.859989639022388, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1535339057445526, "target_z": -0.14062499240155207, "ce": 6.24500846862793, "genuineness": 3.810706615447998, "identity": 0.2877134382724762, "hypothesis": "The 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_Disgust/0588418b012a8bdb1db0120ab91b5327e999484d117da1b0ff5e3902a3153136.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": "0591e28a54ed77b85f649b7a77bdad7a210382a1aff97032a3d17d264529a27b", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b7c645e6abf3282d87f2d63a10ddc9a7b863844d084e29cdacaa9da09f9e2c86", "generation_seconds_batch": 13.644241719972342, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14204320311546326, "target_z": -0.16406249620077604, "ce": 6.086154937744141, "genuineness": 4.218649387359619, "identity": 0.5478005409240723, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comernos pues de comer.", "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_Disgust/0591e28a54ed77b85f649b7a77bdad7a210382a1aff97032a3d17d264529a27b.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "f91521ffa73d227ae083f512a390b213758f0cfaf8b9b89f13c15b60488f0a3a", "generation_seconds_batch": 15.858885405934416, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08075946569442749, "target_z": -0.28906249620077606, "ce": 6.260893821716309, "genuineness": 4.582659721374512, "identity": 0.595787525177002, "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_Disgust/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "0606b6badc57677790c54c999800d3ac68dd85899830e785a1dff04a34d69ac9", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2a1ad7c3597e4b4aee50bd2b31c5fc770d2b9d897bd352ef28b3fc9ae3b5a010", "generation_seconds_batch": 19.459954573074356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11427401006221771, "target_z": -0.22070312025097005, "ce": 5.871703147888184, "genuineness": 4.319066047668457, "identity": 0.6488474011421204, "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_Disgust/0606b6badc57677790c54c999800d3ac68dd85899830e785a1dff04a34d69ac9.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "063ab94661ae793bf896d740626979ed3161571a69d4ebac20c50c2a2506321f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c725361eb95184a0ed3796c99fb72ce7ae589ee31ece1689f0832984a9744aeb", "generation_seconds_batch": 15.961800151038915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1573641300201416, "target_z": -0.1328125113976719, "ce": 5.728734970092773, "genuineness": 4.425758361816406, "identity": 0.5307657718658447, "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_Disgust/063ab94661ae793bf896d740626979ed3161571a69d4ebac20c50c2a2506321f.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "063ca7502adc25188991c7b935aa4b4ef542edf66b65897a8bd82b7ee0d4765d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "be7fb9e4f07b50f1ff289545e7b147d3677a590680758d0a2447c3747520848c", "generation_seconds_batch": 21.104080714052543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15832169353961945, "target_z": -0.13085937594980598, "ce": 6.181467056274414, "genuineness": 4.15588903427124, "identity": 0.549736738204956, "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_Disgust/063ca7502adc25188991c7b935aa4b4ef542edf66b65897a8bd82b7ee0d4765d.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "064ccd082f08de07bb3a09e2a5a18aec02d7fd1cd752b109d31d883aad43394d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8eb481155367ea8efc083c000ceae3fb0e59f420b7fd7fe7666a44c5dda65218", "generation_seconds_batch": 20.27042346005328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.026487082242965698, "target_z": -0.5078125113976719, "ce": 6.332377910614014, "genuineness": 4.017816066741943, "identity": 0.6146005392074585, "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_Disgust/064ccd082f08de07bb3a09e2a5a18aec02d7fd1cd752b109d31d883aad43394d.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "068df2d1578c5e6b1f9f55139af811d0d8a3cf65a43d825cc1674cb45b859d6e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c912e8e9178e3beeeb9ee9d876fc447cab27e957b0729f525610ba8ceee62115", "generation_seconds_batch": 14.82676362991333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07309900224208832, "target_z": -0.30468748860232814, "ce": 6.062326908111572, "genuineness": 4.3127899169921875, "identity": 0.753419041633606, "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_Disgust/068df2d1578c5e6b1f9f55139af811d0d8a3cf65a43d825cc1674cb45b859d6e.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "06dbe1f975dc9f775aa7bf5e1ec22d1a7357a5ec2ad1e2265f3c1ee890c3b9c3", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "28b7b885b1ed3af4a53a0a70aafdaa72375b705936bdca8d3f244d5dee4e67e6", "generation_seconds_batch": 18.919664756977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010857701301574707, "target_z": -0.431640624050194, "ce": 6.197352409362793, "genuineness": 4.7081804275512695, "identity": 0.7672303915023804, "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_Disgust/06dbe1f975dc9f775aa7bf5e1ec22d1a7357a5ec2ad1e2265f3c1ee890c3b9c3.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "06fef1bfee0d44ba80eb111bb1ecd31e67219835c0baa35ff455466807762a4b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c6b00d504ee657ac01f8419ed281936c0efb8b42e5e4ade6dd0514ac2a2c1fae", "generation_seconds_batch": 18.963159556034952, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013730376958847046, "target_z": -0.42578124810038803, "ce": 6.284721851348877, "genuineness": 4.821148872375488, "identity": 0.6818932294845581, "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_Disgust/06fef1bfee0d44ba80eb111bb1ecd31e67219835c0baa35ff455466807762a4b.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "0750bea4959f3eb87aa2c343e7a32da3e3784465c7d130de37c79b6e94c6598e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0eb47f4ca4fdc5d55f716b6f97d4fb8809d44f3a3c344f2292dbb5373f8805ce", "generation_seconds_batch": 15.254098939010873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08363214135169983, "target_z": -0.28320312025097005, "ce": 5.990842819213867, "genuineness": 3.9927117824554443, "identity": 0.7012761831283569, "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_Disgust/0750bea4959f3eb87aa2c343e7a32da3e3784465c7d130de37c79b6e94c6598e.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "0772ed4c4954e790979f035d8a8487cf7a847995f41d931f130228d8d32fbf7a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6823ad3d855d628a3e356fd14539bc8e7cdb5004105a1bb95c438df7c1d26fe8", "generation_seconds_batch": 15.188394636963494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0663960874080658, "target_z": -0.318359375949806, "ce": 6.070269584655762, "genuineness": 3.8671910762786865, "identity": 0.3621686100959778, "hypothesis": "The 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_Disgust/0772ed4c4954e790979f035d8a8487cf7a847995f41d931f130228d8d32fbf7a.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "077961d8eeb25502d6fab1b6f14ecbcac0c2cd3bea450ca52a90ac737c157fb7", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b3fe77bd6d590cf256e7b0b0417c6e0eb3a5a0e5ed0447a45d30735ec55f494d", "generation_seconds_batch": 19.57371441810392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.014996379613876343, "target_z": -0.4843750075984479, "ce": 6.395919322967529, "genuineness": 4.457139015197754, "identity": 0.6285587549209595, "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_Disgust/077961d8eeb25502d6fab1b6f14ecbcac0c2cd3bea450ca52a90ac737c157fb7.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "07e5fe9860bc22c73e24a27c9ba2231f532efc33038599b9790eeb7490748359", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3c45a6ab804907aeb7a69d5afe870c6586b5c624cd3f34bda6723019daf3b669", "generation_seconds_batch": 19.601622223039158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.012123703956604004, "target_z": -0.4785156316486419, "ce": 6.300607204437256, "genuineness": 4.6956281661987305, "identity": 0.6714861392974854, "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_Disgust/07e5fe9860bc22c73e24a27c9ba2231f532efc33038599b9790eeb7490748359.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "0805e9ee31b82a61640b9e4b88ee3f56a24b2c3e52b5f19d0e97628dd1b42b56", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aabab2021a76824f1e8480de854861dc50f84a3746096dc6277af9a5ed2be64e", "generation_seconds_batch": 16.491173104033805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027136191725730896, "target_z": -0.39843750379922394, "ce": 6.356205940246582, "genuineness": 4.519899368286133, "identity": 0.5317416787147522, "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_Disgust/0805e9ee31b82a61640b9e4b88ee3f56a24b2c3e52b5f19d0e97628dd1b42b56.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "0827ab4c99c2653cb00d19d59fc1747ec2cadabff14510048be9769d2dc18e0d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "234dc4b015af567bb00ce5491defe2612d2ebf3b189fe6631ebc6208b7e855c7", "generation_seconds_batch": 16.68964495405089, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.053298696875572205, "target_z": -0.5624999696062083, "ce": 6.419747352600098, "genuineness": 4.306513786315918, "identity": 0.6321452856063843, "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_Disgust/0827ab4c99c2653cb00d19d59fc1747ec2cadabff14510048be9769d2dc18e0d.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "0851a355c2ad51a7606b388b46644c17d84b93e30ee6c9480028b7d0fd2ea4f2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aa3c91c07d730acd2099937f9de84c90187894da69a66df0325df986f4b70ad2", "generation_seconds_batch": 19.44551635091193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.10692198574542999, "target_z": -0.6718750075984479, "ce": 6.252951145172119, "genuineness": 4.306513786315918, "identity": 0.35294783115386963, "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_Disgust/0851a355c2ad51a7606b388b46644c17d84b93e30ee6c9480028b7d0fd2ea4f2.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "0879299167d10c884139746e2052e1c02cd8fa87c07372c47c4f748d610c9969", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0fa757c8715c09d56962a67e02040bbe902c46b9db6dc7e4a91e0f0d52e7c688", "generation_seconds_batch": 18.920137204928324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13629785180091858, "target_z": -0.17578124810038803, "ce": 6.141753673553467, "genuineness": 3.653805732727051, "identity": 0.5254460573196411, "hypothesis": "The 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_Disgust/0879299167d10c884139746e2052e1c02cd8fa87c07372c47c4f748d610c9969.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "08a193dc6d00cdd8a46773c4cfaf739458047c6266903019d4a633ee2d0ed707", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ee34a4da1cbabc785a0cce5e163cbe23e274e98a87043855ad40c7820649d340", "generation_seconds_batch": 21.140355481998995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.012123703956604004, "target_z": -0.4785156316486419, "ce": 6.332377910614014, "genuineness": 4.532451152801514, "identity": 0.6536301970481873, "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_Disgust/08a193dc6d00cdd8a46773c4cfaf739458047c6266903019d4a633ee2d0ed707.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "0924545fc00a5c43b8fcc7e34f5f47869e4a5fa14ae75084bb195f25e66b90bb", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fefa92d9b403ac7e0318fe792b0f5d62ab115ea584c1d8897162ce378e40e318", "generation_seconds_batch": 19.015857640071772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.052990272641181946, "target_z": -0.34570312025097005, "ce": 5.839932441711426, "genuineness": 4.344170093536377, "identity": 0.7828696966171265, "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_Disgust/0924545fc00a5c43b8fcc7e34f5f47869e4a5fa14ae75084bb195f25e66b90bb.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": "096a12a325b52d19cbe69853498a17975a0eccf758e8a313919718eac02fb5d6", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "099e7b210ef5150c21be12e3091990b72f80ec70e853fe1e9eb93b458eed61a3", "generation_seconds_batch": 13.671508171013556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2030179500579834, "target_z": 2.000000091181375, "ce": 5.982900142669678, "genuineness": 3.7793264389038086, "identity": 0.7777470946311951, "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_Disgust/096a12a325b52d19cbe69853498a17975a0eccf758e8a313919718eac02fb5d6.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "09ef9916f38fea3a2f48dd0b46ac92a5c994ee8753d9c5d31f00cc67c2d03619", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "b45f3542b20455658ee57f904ce5c9e64d83ce50e1b35a98d90b88ba953130ee", "generation_seconds_batch": 16.35766903392505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0252210795879364, "target_z": -0.40234374430116404, "ce": 6.2767791748046875, "genuineness": 4.570107460021973, "identity": 0.8406599760055542, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/09ef9916f38fea3a2f48dd0b46ac92a5c994ee8753d9c5d31f00cc67c2d03619.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "0a438f14963541a911b2e5d32fb915c9021d9696b2329502210b6d3ccc5fd86e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aea828c0fd7f0a91a12747c1c80a6e833ad5c7d360ccc9d9e57a2678e619f0dd", "generation_seconds_batch": 18.94623301899992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17651531100273132, "target_z": -0.09374998480310416, "ce": 6.173524379730225, "genuineness": 4.400654315948486, "identity": 0.6604710817337036, "hypothesis": "Die Tür 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_Disgust/0a438f14963541a911b2e5d32fb915c9021d9696b2329502210b6d3ccc5fd86e.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": "0a56eda34a14a0c13ba2b7fee1a74d1333fdf5a414df765c28be8d88d188306c", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c744ea86139bac6d45f7237c6895f2b6a6c51d3077a6d1631fc06d89dbfac40d", "generation_seconds_batch": 13.596160667017102, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1717275083065033, "target_z": -0.10351563164864193, "ce": 5.998785495758057, "genuineness": 3.7918784618377686, "identity": 0.5622262358665466, "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_Disgust/0a56eda34a14a0c13ba2b7fee1a74d1333fdf5a414df765c28be8d88d188306c.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "0a87e99eceb9cf798998ad9148ea580bda7bc49c3bb0348b58b0b735e5772bb9", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "df3b75512bebf91725c1e20303996f78385cc5d66bcc39ad32e96890bde43b8a", "generation_seconds_batch": 19.015996044967324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03606267273426056, "target_z": -0.5273437746949557, "ce": 6.38797664642334, "genuineness": 4.030367851257324, "identity": 0.6329229474067688, "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_Disgust/0a87e99eceb9cf798998ad9148ea580bda7bc49c3bb0348b58b0b735e5772bb9.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "0a8fa64a6fb0a9832154c38a1ce644d34eb7950b81ddebc61a76c710b03aea08", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e8b098913fe610f28a65739eb2079af95d2530c236ecdfc61b259a9866822c5a", "generation_seconds_batch": 15.97963591804728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08171702921390533, "target_z": -0.28710936075291016, "ce": 6.252951145172119, "genuineness": 4.7332844734191895, "identity": 0.45090359449386597, "hypothesis": "Die Tür 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_Disgust/0a8fa64a6fb0a9832154c38a1ce644d34eb7950b81ddebc61a76c710b03aea08.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "0b61c59a7865af441f13d71a57c2642f2ceb2051fd175d0fa85544a9b00b2fdd", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "de2a86fb98f08499ffefc7602fbac5f70d3a00e206238bcccf5bf2ec1374ef81", "generation_seconds_batch": 19.54892632504925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09512284398078918, "target_z": -0.25976561645174606, "ce": 6.141753673553467, "genuineness": 4.193545341491699, "identity": 0.5689355134963989, "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_Disgust/0b61c59a7865af441f13d71a57c2642f2ceb2051fd175d0fa85544a9b00b2fdd.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "0ba4712e8602736df4065c9b93c0eb8d58cb180f7f9772c83c534eeaaf3b8748", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f677fa8cc2243da58c4d4d297f2df9892024acd8784b85421fea99e5f61beb6d", "generation_seconds_batch": 18.877850693068467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17460018396377563, "target_z": -0.09765625569883594, "ce": 6.0146708488464355, "genuineness": 4.369274139404297, "identity": 0.7389402389526367, "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_Disgust/0ba4712e8602736df4065c9b93c0eb8d58cb180f7f9772c83c534eeaaf3b8748.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "0bb2d1145c37498ffd7e293effe7624be0ba3a01c02ad5c2ee35cf33b0a74883", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a1400c6fa524457c0bf9463b414f18d1362411d2fc6d9020b49aeec1e07c2e69", "generation_seconds_batch": 14.72270370007027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2899859845638275, "target_z": 0.13769533482044077, "ce": 6.23706579208374, "genuineness": 4.005263805389404, "identity": 0.6728464365005493, "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_Disgust/0bb2d1145c37498ffd7e293effe7624be0ba3a01c02ad5c2ee35cf33b0a74883.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "0bb3e1a3778f77c169ffdb779f679cec450883c440e582389c5b11056a54732c", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9d0aec72229ca33fa450a1abc357a924637c4138e1deec0b57d4ea19a987d7e1", "generation_seconds_batch": 16.098389495979063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08841992914676666, "target_z": -0.27343750379922394, "ce": 6.292664527893066, "genuineness": 3.9048471450805664, "identity": 0.3252915143966675, "hypothesis": "The 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_Disgust/0bb3e1a3778f77c169ffdb779f679cec450883c440e582389c5b11056a54732c.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "0c2479cb167c8fb816a55673a6b51957311822984b4ee1eca3382188aab0d15b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc3a56ccb96d3e8e5c6fc316d8356cbfb0fefc9986145c59f9cc2ea546f4de61", "generation_seconds_batch": 14.983021041029133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04532980918884277, "target_z": -0.3613281126525221, "ce": 6.173524379730225, "genuineness": 4.545003414154053, "identity": 0.6451033353805542, "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_Disgust/0c2479cb167c8fb816a55673a6b51957311822984b4ee1eca3382188aab0d15b.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "0c2ef6fa1c6bd788003b727d48f58bccf8610fd16d87a891f0b3b3499d1ff871", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "86ace7253e4fd8186c04ac15551542dd7f8724469f42173201d87a3b8bc2b124", "generation_seconds_batch": 18.882588249980472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0076760053634644, "target_z": 1.6015625265945677, "ce": 5.95112943649292, "genuineness": 3.6914620399475098, "identity": 0.5085993409156799, "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_Disgust/0c2ef6fa1c6bd788003b727d48f58bccf8610fd16d87a891f0b3b3499d1ff871.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "0c35b59b821fa0d02c8bada7e76d12768b883e73184890bb196c3b57365224b9", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8778451a3ac80bc6a5d9371f8edd6498ae31fe0479dbaf7be7837f3178e0214d", "generation_seconds_batch": 18.78386472002603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016603052616119385, "target_z": -0.419921872150582, "ce": 6.2767791748046875, "genuineness": 4.168440818786621, "identity": 0.47338002920150757, "hypothesis": "The 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_Disgust/0c35b59b821fa0d02c8bada7e76d12768b883e73184890bb196c3b57365224b9.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "0c451397a2b30a5c19cb465206c2d03b1d7368fcefe808ec221b65629ff405f2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ae2ade8b8388569a35034d37dbb2b871b06d704fd0a8e6cae78fb9c550b74c22", "generation_seconds_batch": 22.514783828053623, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03383910655975342, "target_z": -0.38476561645174606, "ce": 6.324435234069824, "genuineness": 4.356721878051758, "identity": 0.5086976289749146, "hypothesis": "The 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_Disgust/0c451397a2b30a5c19cb465206c2d03b1d7368fcefe808ec221b65629ff405f2.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "0c75cd65fca7e89c75c5e08d53592ec6eae8a66e5561abd990851e4763ca37ac", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "578ed97f297b4dcc2d7dfb4d1ec692ee77cbb0df39ddefbb01d955c415909146", "generation_seconds_batch": 19.522687333985232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09991063177585602, "target_z": -0.25, "ce": 6.332377910614014, "genuineness": 4.532451152801514, "identity": 0.7186896204948425, "hypothesis": "Die Tür 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_Disgust/0c75cd65fca7e89c75c5e08d53592ec6eae8a66e5561abd990851e4763ca37ac.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "0c984c7b4b2ab5eaa34282f8c873b19e38790f071a85e564656da0379c947233", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d80632c2e8f30b9070f9d3d69e653522adaabd87510c68c130f259e6c84b7ad6", "generation_seconds_batch": 19.610767800942995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07597167789936066, "target_z": -0.2988281126525221, "ce": 6.229123115539551, "genuineness": 4.231201171875, "identity": 0.5787651538848877, "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_Disgust/0c984c7b4b2ab5eaa34282f8c873b19e38790f071a85e564656da0379c947233.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "0c9f495e9be8a1379e188836d9e0afbfa42d7ab756a7bc4b6363cc267b289ce2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cd39eeec97fa6e57d16bb3fd6ecd53c7541aef8b071fa6d5e7cdd9d28e081a82", "generation_seconds_batch": 18.928393620066345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00829346477985382, "target_z": -0.47070312025097005, "ce": 6.292664527893066, "genuineness": 4.432034492492676, "identity": 0.4768333435058594, "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_Disgust/0c9f495e9be8a1379e188836d9e0afbfa42d7ab756a7bc4b6363cc267b289ce2.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "d92036fe8c0dd3badac2d2e5386c0434297b14e985f246af78e05a00d7e12ddb", "generation_seconds_batch": 14.141342513030395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.042457133531570435, "target_z": -0.36718748860232814, "ce": 6.141753673553467, "genuineness": 4.20609712600708, "identity": 0.7955098152160645, "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_Disgust/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "0cbee3a0bc879ce4b86d406f9418d2b31c78a4e88c2917b197592c86e8a16c18", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "85518b947306bc03065dc645e65df18dd779f49afa26a409c084c8e721a292d3", "generation_seconds_batch": 13.71900565805845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3367671966552734, "target_z": 4.312500303937917, "ce": 6.165581703186035, "genuineness": 3.525146961212158, "identity": 0.4021119475364685, "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_Disgust/0cbee3a0bc879ce4b86d406f9418d2b31c78a4e88c2917b197592c86e8a16c18.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "0d16413d59845fc99ed6f3989fb98c6c401b9315b8c88c418e80a9742262715f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fbbd263c0268c7b52f34a7510eede92dc0252f9d075d55f88fcca0906dc2d7ef", "generation_seconds_batch": 20.28178406599909, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.091292604804039, "target_z": -0.267578127849418, "ce": 6.38797664642334, "genuineness": 4.645420074462891, "identity": 0.7544641494750977, "hypothesis": "Die Tür 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_Disgust/0d16413d59845fc99ed6f3989fb98c6c401b9315b8c88c418e80a9742262715f.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "0d244d8593a68cbc04d7dacb781352fa57fa878eb5909ce7071ce130d301cf7b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ef8ec5b5d952fc0de078e50baa0fe727ec3ade83bd5bd3ebb759841fb2687df9", "generation_seconds_batch": 18.980662252986804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06926876306533813, "target_z": -0.3125, "ce": 5.982900142669678, "genuineness": 4.13078498840332, "identity": 0.47361913323402405, "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_Disgust/0d244d8593a68cbc04d7dacb781352fa57fa878eb5909ce7071ce130d301cf7b.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": "0da1bfa441367bc2454aad3184636dc238d29adfc7b8307318870c2af7e2627a", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "289ad486579feeee34d5b462b41c32f8290937fc7b727ee6110144810a08cadd", "generation_seconds_batch": 13.833165045944043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23684148490428925, "target_z": 0.02929687974902995, "ce": 6.0146708488464355, "genuineness": 4.250029563903809, "identity": 0.6219724416732788, "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": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/0da1bfa441367bc2454aad3184636dc238d29adfc7b8307318870c2af7e2627a.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "0e30e8699b29e7bb0aebd30fd2b9f934b2b255af3c65691e99aeb49d97aaef89", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cf50bb264db7f46db45b9c3d3da4206e707fe798546757a9cf1bb350879032fe", "generation_seconds_batch": 18.738074940047227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.04180802404880524, "target_z": -0.5390625265945678, "ce": 6.197352409362793, "genuineness": 4.6203155517578125, "identity": 0.6859719157218933, "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_Disgust/0e30e8699b29e7bb0aebd30fd2b9f934b2b255af3c65691e99aeb49d97aaef89.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "0f0db8b6bf2f8dc15a3b92c25600fb60b164e240928d7fb1eaa028c9139d9f08", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5963fe1779cde1298b9636a6ddbc79c8e5a2b6963f8097792cedc6355f1f143b", "generation_seconds_batch": 18.59410536091309, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03414754569530487, "target_z": -0.5234375037992239, "ce": 6.23706579208374, "genuineness": 3.7667744159698486, "identity": 0.44078201055526733, "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_Disgust/0f0db8b6bf2f8dc15a3b92c25600fb60b164e240928d7fb1eaa028c9139d9f08.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "0faae23c008cd761037b083b364fbec242dbb0d2ad8fda95d60ca706ae8b3e8b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8a2486ab79f4bc9a0048c344556daebc98b61cd20c1dded331339dca567bb3a2", "generation_seconds_batch": 22.7997506079264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.04372312128543854, "target_z": -0.5429687367027162, "ce": 6.403861999511719, "genuineness": 4.821148872375488, "identity": 0.6308670043945312, "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_Disgust/0faae23c008cd761037b083b364fbec242dbb0d2ad8fda95d60ca706ae8b3e8b.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "0facb66043430f59d9effa6e5b45d45804256b7d0e9adba93989660b9287c20a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "03fba446f199b88a7832f389eae67c69a5b29a801397d93431f78ac1db48ae8a", "generation_seconds_batch": 21.177830273984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08554725348949432, "target_z": -0.27929687974902995, "ce": 6.09409761428833, "genuineness": 4.300237655639648, "identity": 0.7049793004989624, "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_Disgust/0facb66043430f59d9effa6e5b45d45804256b7d0e9adba93989660b9287c20a.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "0fe0c1374cb5bada9f05caf459266dd7e74b8e40d192ef044ee610b811d4584d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "1712e7e7a96189a9be7751753d62f6105d65fe12943e9edb432ef86223448bb2", "generation_seconds_batch": 13.892647490021773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.022656843066215515, "target_z": -0.5, "ce": 6.268836498260498, "genuineness": 3.8546390533447266, "identity": 0.5874291658401489, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/0fe0c1374cb5bada9f05caf459266dd7e74b8e40d192ef044ee610b811d4584d.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "101ee6290fa7a2ea9d75e7721b18c50416fdf95b938ea638eaa3d2c83f8a20b4", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3e425b92bc81987a57b1852406a4c75b94a0df327e51af222e3a38ba109292f0", "generation_seconds_batch": 18.6227251640521, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21864786744117737, "target_z": -0.007812511397671884, "ce": 5.855817794799805, "genuineness": 3.5565271377563477, "identity": 0.30265676975250244, "hypothesis": "The 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_Disgust/101ee6290fa7a2ea9d75e7721b18c50416fdf95b938ea638eaa3d2c83f8a20b4.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "1037e825e6f41ae6ec4b5cd90d14bc8335a3057d369878b600ee8a10736f8457", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "3e856186ced96138711956a41938534a76ee08f0a4388cea169d04995fa782c7", "generation_seconds_batch": 18.839402387966402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.04180802404880524, "target_z": -0.5390625265945678, "ce": 6.2767791748046875, "genuineness": 4.432034492492676, "identity": 0.7980779409408569, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/1037e825e6f41ae6ec4b5cd90d14bc8335a3057d369878b600ee8a10736f8457.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "107ad376ca6f6f8ddb05b3a82b7037b0d4710377838e13faecf2f8cbea4ae93b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b75c6790a846aa737dd5d4ec44cd652c877b827368e83442096d03f7d61b04d1", "generation_seconds_batch": 18.97944925702177, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18992112576961517, "target_z": -0.06640624050194009, "ce": 6.070269584655762, "genuineness": 4.218649387359619, "identity": 0.5232318639755249, "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_Disgust/107ad376ca6f6f8ddb05b3a82b7037b0d4710377838e13faecf2f8cbea4ae93b.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "10d80e9b88ec9ceda598b923a8a14cc505e4468c73c0e5a84935c85e1cd8434e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "20a8512218ffcb918f1525499d57394b7eea3cf1c83ac3081e8eda8ab3d6814f", "generation_seconds_batch": 16.21632698306348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0003245621919631958, "target_z": -0.4531249924015521, "ce": 6.427689552307129, "genuineness": 4.532451152801514, "identity": 0.6894729137420654, "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_Disgust/10d80e9b88ec9ceda598b923a8a14cc505e4468c73c0e5a84935c85e1cd8434e.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": "10ec8cfe66409ac52fa357130ec4ec3b2b2776c5673b1c9ff0bfbf224e24753d", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ed389caf038373bce275108256914b70abf50deabb68c4f12620464e1eba6239", "generation_seconds_batch": 18.728912401013076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0038458108901978, "target_z": 1.5937501063782709, "ce": 6.197352409362793, "genuineness": 3.8671910762786865, "identity": 0.4414709210395813, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik laste twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "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_Disgust/10ec8cfe66409ac52fa357130ec4ec3b2b2776c5673b1c9ff0bfbf224e24753d.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "110ab5b30a92e7858e6c3c8df94bba70985112f78fa66d462e51046ddb3c0ac8", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "510cac4955a0fcddb90603d5bf1cadd470058ea7cd579d17b354570787f1ba87", "generation_seconds_batch": 13.84536940290127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09703795611858368, "target_z": -0.255859375949806, "ce": 6.181467056274414, "genuineness": 3.7667744159698486, "identity": 0.24787487089633942, "hypothesis": "The 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_Disgust/110ab5b30a92e7858e6c3c8df94bba70985112f78fa66d462e51046ddb3c0ac8.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "11168a965e08581df82eac308cb03660da0a347e1426eca71e53399199e94e5f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "602c132d06d2ecab3eb4d15c8ebdf8fa7546a0d3509b70c9b85f369528ffc2da", "generation_seconds_batch": 13.68504132295493, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08458970487117767, "target_z": -0.28124998480310415, "ce": 6.268836498260498, "genuineness": 4.570107460021973, "identity": 0.6444332599639893, "hypothesis": "Die Tür 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_Disgust/11168a965e08581df82eac308cb03660da0a347e1426eca71e53399199e94e5f.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": "111b96f1619b8baea4e3d3583d3a89c1054ee55dcc30f107dad0c7f919b6cdde", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "df2ca8db6f64c2b986acc75d92c2bb92300efd4ed63a5419c0437e5a3c7427a3", "generation_seconds_batch": 19.641047214972787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4481528997421265, "target_z": 2.500000091181375, "ce": 5.80021858215332, "genuineness": 3.9048471450805664, "identity": 0.46214407682418823, "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": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/111b96f1619b8baea4e3d3583d3a89c1054ee55dcc30f107dad0c7f919b6cdde.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "11508dee665d99baadf8506ae14d1070e8ed2965fbb2aba0040e59eacb801d9f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "df3c5e2d87cc548410a9a34ae3c56217128b789cd9e9efff48f5a722e6a51618", "generation_seconds_batch": 13.83555441396311, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04916003346443176, "target_z": -0.3535156316486419, "ce": 5.871703147888184, "genuineness": 4.331617832183838, "identity": 0.7542710900306702, "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_Disgust/11508dee665d99baadf8506ae14d1070e8ed2965fbb2aba0040e59eacb801d9f.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "11a5fd8e391edfed1506a89631d51bdc556ba31c7e68da70bd33aaaa04b29497", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fc947ef9daa893917ae8af0aeaa274f0bf8b08ea7e6dff2af781ed786c89751c", "generation_seconds_batch": 18.877850693068467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1592792570590973, "target_z": -0.1289062405019401, "ce": 6.0146708488464355, "genuineness": 4.331617832183838, "identity": 0.6318755745887756, "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_Disgust/11a5fd8e391edfed1506a89631d51bdc556ba31c7e68da70bd33aaaa04b29497.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "11c92ed397bfc2ec801b1d41fee9c0a2092234aa100cf7a441c1665d3b3ecbf0", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "7b13b05129ec2c5c6999fa36793b289539c516a557cf1839347ecc92dc8ab369", "generation_seconds_batch": 18.83066588593647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.013081252574920654, "target_z": -0.4804687367027161, "ce": 6.324435234069824, "genuineness": 3.9676074981689453, "identity": 0.4668792188167572, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/11c92ed397bfc2ec801b1d41fee9c0a2092234aa100cf7a441c1665d3b3ecbf0.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": "11eca53a457e83a64672307e2e190d1e93d14e7b7cb00bd5d497b907f720317e", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1a893121e022e784e424a6cdf5b53c120e19a7168e2f20316165edd5121cc8ca", "generation_seconds_batch": 18.758354914025404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20045426487922668, "target_z": -0.04492187215058203, "ce": 5.911416053771973, "genuineness": 3.961331605911255, "identity": 0.6162757277488708, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, lié-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_Disgust/11eca53a457e83a64672307e2e190d1e93d14e7b7cb00bd5d497b907f720317e.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": "122fecae37d81c6243711fe9e217320d2badcc34a41ef74cb1b0117addfd1cef", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "32ddd00a185bd1d3128eed7c100d47e80369178e53102ea572f2fdfc11d93bc9", "generation_seconds_batch": 13.584538255003281, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12384959310293198, "target_z": -0.20117187215058202, "ce": 5.510311126708984, "genuineness": 4.005263805389404, "identity": 0.7141778469085693, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, le bien, et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/122fecae37d81c6243711fe9e217320d2badcc34a41ef74cb1b0117addfd1cef.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "12573af402b6dcb397893026b78fd737ba5f4b95182fa87bafaba48074f1e2e2", "bucket": "emo_Disgust", "phase": "wording", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c59425c3361c9e40c424b3cac0ed67ff0d4d7db74dff5b7ca26b3f5afd6f4296", "generation_seconds_batch": 14.042485764017329, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08746236562728882, "target_z": -0.27539063924708984, "ce": 6.197352409362793, "genuineness": 4.356721878051758, "identity": 0.6536509394645691, "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_Disgust/12573af402b6dcb397893026b78fd737ba5f4b95182fa87bafaba48074f1e2e2.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": "127a717afae20829484bbfc032678f58155af812a15f7a40627659744e0cc529", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "363b9ecb43d871b14b9cbab1d56866f618ddf7e68952cef1998d1ed8b6ebdaa5", "generation_seconds_batch": 18.531115247053094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.187696933746338, "target_z": 1.9687499240155208, "ce": 6.0146708488464355, "genuineness": 4.13078498840332, "identity": 0.6514583230018616, "hypothesis": "De sleutels liggen op op de keukentafel. Ik keek in de laag en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/127a717afae20829484bbfc032678f58155af812a15f7a40627659744e0cc529.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "bb8710f5050daa0ca101c313428c5567b92ea420d958934e2f64a3b31f0d38d4", "generation_seconds_batch": 13.69885648903437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0520327091217041, "target_z": -0.34765625569883596, "ce": 6.125868320465088, "genuineness": 4.293961524963379, "identity": 0.7088432312011719, "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_Disgust/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.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": "12c45bee39adf2dceb13c332f6a4178021adc85d74ae6bda04c3845ebc399538", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Your message arrived after I had left.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4bf549c5a35f4979db7ea38993f5eea6e2104a39e85a1d599c40d5edee5f97e", "generation_seconds_batch": 13.612508848891594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3536636233329773, "target_z": 0.2675781582432097, "ce": 5.6254801750183105, "genuineness": 3.6349775791168213, "identity": 0.2873566448688507, "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_Disgust/12c45bee39adf2dceb13c332f6a4178021adc85d74ae6bda04c3845ebc399538.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "135d4bbd0ed8d20e82a9470c268c625895682cb84776dffcda69f39356e6095d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "90959c2f16adc57f2562cf3c3dc9948f752228629f1db6cb631c44d32397e9f7", "generation_seconds_batch": 14.094774086028337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0006330013275146484, "target_z": -0.455078127849418, "ce": 6.3641486167907715, "genuineness": 4.068024158477783, "identity": 0.587182879447937, "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_Disgust/135d4bbd0ed8d20e82a9470c268c625895682cb84776dffcda69f39356e6095d.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "139af1bbf32477ad5b0151bd5e66802c65da02718756a22e65db85307462a3de", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "85455f7fe450903ddd8b18346ceff4cf509aae504a87ae5512484eb90b389f1f", "generation_seconds_batch": 18.6535364020383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9119201302528381, "target_z": 1.4062499544093126, "ce": 6.1020402908325195, "genuineness": 4.2751336097717285, "identity": 0.4536478817462921, "hypothesis": "Die Tür 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_Disgust/139af1bbf32477ad5b0151bd5e66802c65da02718756a22e65db85307462a3de.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "13c6324c0d3340503cf86219d9b739f8ee2f0675f9a4ac04726b57a84656aec0", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "79d69bc36b233187ad56e9426d486e5bd098c5a314fd1010b12f3198bb03b57f", "generation_seconds_batch": 18.883487040991895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005112349987030029, "target_z": -0.443359375949806, "ce": 6.348263263702393, "genuineness": 4.469690799713135, "identity": 0.6326944828033447, "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_Disgust/13c6324c0d3340503cf86219d9b739f8ee2f0675f9a4ac04726b57a84656aec0.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "1419f83a0954fbf677e29d7bc6d17e77ef939c0e10a794371b53c5bdac552572", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e49524d7ae4077408867e69e01a6f736eb71c55a2ebfbf49a9d8c42b789dfaec", "generation_seconds_batch": 13.75426655204501, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.547739028930664, "target_z": 2.703125205158094, "ce": 5.796247482299805, "genuineness": 3.5439748764038086, "identity": 0.458685040473938, "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_Disgust/1419f83a0954fbf677e29d7bc6d17e77ef939c0e10a794371b53c5bdac552572.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "141ab8f422a5df891ed1c752699bc3a7b9b55c4ea31b7b5eec6032c35200bf21", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a0abc21ae43a7159afb6480c44a8cb0bed5a85e1cebc94ec7479a74fcd3cf27e", "generation_seconds_batch": 18.999710357980803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.013081252574920654, "target_z": -0.4804687367027161, "ce": 6.24500846862793, "genuineness": 4.519899368286133, "identity": 0.6736757755279541, "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_Disgust/141ab8f422a5df891ed1c752699bc3a7b9b55c4ea31b7b5eec6032c35200bf21.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "145bbab71bfdb88471061c866d73ea2dcef493451d7beaa8afb816fb102c7afc", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5a252ce83a5ede645811b79e0c400d12ca9b9d33b1b506527c21e6b017b4cd11", "generation_seconds_batch": 18.831923750927672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7893526554107666, "target_z": 1.1562499544093126, "ce": 5.959072113037109, "genuineness": 3.9173994064331055, "identity": 0.501247763633728, "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_Disgust/145bbab71bfdb88471061c866d73ea2dcef493451d7beaa8afb816fb102c7afc.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "14b16ea67829ebfd709b6206dee8961de1310296867c0f73c7751b91c95105a6", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "421f00b19a990078e9697e9e2340b9e2f2053174deb6b1bf43a5f3bfbfcae196", "generation_seconds_batch": 18.92304601892829, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07405655086040497, "target_z": -0.30273438354825394, "ce": 6.340320587158203, "genuineness": 4.111956596374512, "identity": 0.49059104919433594, "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_Disgust/14b16ea67829ebfd709b6206dee8961de1310296867c0f73c7751b91c95105a6.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "14c808469b3f1c7cc9143dd35456cdeecf1772de79202c3441acc149e7163065", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "940c5ebba8476d192fa3f264272e59e1f4acd0d8a640012fea39a2af43597445", "generation_seconds_batch": 16.21632698306348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019475728273391724, "target_z": -0.41406249620077606, "ce": 5.990842819213867, "genuineness": 4.482243061065674, "identity": 0.742466926574707, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinspringen.", "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_Disgust/14c808469b3f1c7cc9143dd35456cdeecf1772de79202c3441acc149e7163065.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "23c3d767b5330b46740e122a9fde3174aaaaf44ec7bf096fce0670725e2051a6", "generation_seconds_batch": 13.69517502200324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03671178221702576, "target_z": -0.3789062405019401, "ce": 6.324435234069824, "genuineness": 4.507347106933594, "identity": 0.5073915719985962, "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_Disgust/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "15cb9cae46b28b5a74108f62b7b0e9051b0e22b037c6c9a7a71a3c90136ab58d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0be69971323210be2f451ad497238089dec5e0decc18347618b3fe1ae565eca5", "generation_seconds_batch": 19.522687333985232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07980190217494965, "target_z": -0.2910156316486419, "ce": 6.38003396987915, "genuineness": 4.7081804275512695, "identity": 0.48051542043685913, "hypothesis": "Die Tür 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_Disgust/15cb9cae46b28b5a74108f62b7b0e9051b0e22b037c6c9a7a71a3c90136ab58d.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "1640958d8b29e50c9034400f8bbc6f3e9374330944ca70feff718d30716f7967", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1a2b7c66e7077c737385d4119751308abd4f644bcf527fb1197ff186771aa032", "generation_seconds_batch": 13.808131155907176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09895307570695877, "target_z": -0.25195312025097005, "ce": 6.292664527893066, "genuineness": 4.005263805389404, "identity": 0.6643322706222534, "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_Disgust/1640958d8b29e50c9034400f8bbc6f3e9374330944ca70feff718d30716f7967.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "1646c897fe6c5283c8837b10a792738e2229a25bba9065e694281a20f49b9962", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a8b638bdcfee266e69a76c34cb741aa2d9140f08d4e08b2e797daae1349b3fc4", "generation_seconds_batch": 20.275206129066646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.06861965358257294, "target_z": -0.5937500151968959, "ce": 6.2767791748046875, "genuineness": 4.105680465698242, "identity": 0.45938023924827576, "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_Disgust/1646c897fe6c5283c8837b10a792738e2229a25bba9065e694281a20f49b9962.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "1752fe1855a2fa097d77ac8dfb435babc1b3ecf7471b30cd0fa7da59d9600de2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "94a04fcbceef363e503e8310288911cf2056c05b865671a31342d095e0ec6c71", "generation_seconds_batch": 18.886185772018507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1535339057445526, "target_z": -0.14062499240155207, "ce": 6.062326908111572, "genuineness": 3.9425034523010254, "identity": 0.368255078792572, "hypothesis": "The 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_Disgust/1752fe1855a2fa097d77ac8dfb435babc1b3ecf7471b30cd0fa7da59d9600de2.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": "177beed048e00974120a9a7d35e6bb0e51dab319b40678615bf7608f0d5a5907", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The road turns left behind the bridge.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0427296f193a7fbc6de321de046b499a846932ef0f9bb8b1926a5d0e5b9cab80", "generation_seconds_batch": 18.694081041030586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1267222762107849, "target_z": -0.19531248100388018, "ce": 6.292664527893066, "genuineness": 3.6224255561828613, "identity": 0.30649834871292114, "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_Disgust/177beed048e00974120a9a7d35e6bb0e51dab319b40678615bf7608f0d5a5907.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "18c6c0f86137d5e9403a84acc633b9128e012a88aabf65bd822ca8369ca74c9f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4d096c7236a392f9c28b6a66e2f1f8891a2611643315484439cbd924bf2c3d22", "generation_seconds_batch": 15.188394636963494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03192397952079773, "target_z": -0.3886718873474779, "ce": 6.316492557525635, "genuineness": 3.835810661315918, "identity": 0.4613240361213684, "hypothesis": "The 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_Disgust/18c6c0f86137d5e9403a84acc633b9128e012a88aabf65bd822ca8369ca74c9f.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "192934801197aa1d4cf956fbe9a3a54784edac3685a7ad1d272267f84983d8c4", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "66b3116c3b9250d4991b54da835889acfd6e58c189b6bbbc0656c1b7d91d2761", "generation_seconds_batch": 22.661220000009052, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.07436500489711761, "target_z": -0.6054687670965079, "ce": 6.252951145172119, "genuineness": 4.21237325668335, "identity": 0.575903594493866, "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_Disgust/192934801197aa1d4cf956fbe9a3a54784edac3685a7ad1d272267f84983d8c4.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "19342133520741ddde5ad2566ccae9e4e6fb99dc4569d0d7a6f9115110bf4200", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9639340068ac12a4413eab5ceed80c87492203fb75d3bcf8d8bc4793f3154fd6", "generation_seconds_batch": 18.89746289595496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.842975914478302, "target_z": 1.2656249316139687, "ce": 6.24500846862793, "genuineness": 4.168440818786621, "identity": 0.614315927028656, "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_Disgust/19342133520741ddde5ad2566ccae9e4e6fb99dc4569d0d7a6f9115110bf4200.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "196353158ea5240e223dbcd40b5ac954d757ab4dcc59abb02eb2d3e1317ec16d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "63d4be37b3b1eebaa199f176e2883cda3e0b230d9f1ee43b88885b7bda8dccfa", "generation_seconds_batch": 18.783591369981878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07309900224208832, "target_z": -0.30468748860232814, "ce": 6.268836498260498, "genuineness": 4.7081804275512695, "identity": 0.8018066883087158, "hypothesis": "Die Tür 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_Disgust/196353158ea5240e223dbcd40b5ac954d757ab4dcc59abb02eb2d3e1317ec16d.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "1ae68a1afd3620534bd8485838243cd757cb5e5b0a8ea358b31340abfb5bb201", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ba613ba710d4e677fa2c834eb490558fa7a51c4265b8f1c21c783908c0de4c1f", "generation_seconds_batch": 20.893441542051733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08075946569442749, "target_z": -0.28906249620077606, "ce": 6.221180438995361, "genuineness": 4.507347106933594, "identity": 0.38986942172050476, "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_Disgust/1ae68a1afd3620534bd8485838243cd757cb5e5b0a8ea358b31340abfb5bb201.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": "1bac992900e4cfd6ea8fa863d98c2dc9660c23a6a2abe9aa07122ac537abce5c", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Escribí el número en el sobre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "869c5fd7f367c9eb0b6db180a411a42df457db2f2fa44a00bebe51120d1bb5eb", "generation_seconds_batch": 18.529036583960988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18704845011234283, "target_z": -0.07226561645174609, "ce": 6.229123115539551, "genuineness": 4.005263805389404, "identity": 0.7280707359313965, "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_Disgust/1bac992900e4cfd6ea8fa863d98c2dc9660c23a6a2abe9aa07122ac537abce5c.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": "1bbfc5f5306c80e281f2b2ada786e524a5005746fbed4b09f3055e47e7506d0c", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dc0a2e0d7833b2bd9967e61c0326b219e68aa3ae3c0458e4be9c70a589a76f88", "generation_seconds_batch": 13.68820621795021, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1573641300201416, "target_z": -0.1328125113976719, "ce": 6.221180438995361, "genuineness": 4.105680465698242, "identity": 0.5701987743377686, "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_Disgust/1bbfc5f5306c80e281f2b2ada786e524a5005746fbed4b09f3055e47e7506d0c.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "1bd6da963a8645074b778ad285d630c6599beb3e57bb03515c6c41881c42981c", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "96a5bcb976dad7bba89bb88ab62a3aac14bbfa51ba53914dde9e316d4b60bdee", "generation_seconds_batch": 21.014618846937083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.478794813156128, "target_z": 2.5625001823627502, "ce": 6.221180438995361, "genuineness": 3.7165660858154297, "identity": 0.6255089044570923, "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_Disgust/1bd6da963a8645074b778ad285d630c6599beb3e57bb03515c6c41881c42981c.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "1c0d7f87ca89369224409fa44c6b9c4917616f846c108e06af2ab1a028eacdac", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "636ed7747bd29e8057379ac969931c1d76ce3d849e599006e4f2e7f1356c154d", "generation_seconds_batch": 18.94623301899992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08650481700897217, "target_z": -0.27734374430116404, "ce": 6.149696350097656, "genuineness": 4.720732688903809, "identity": 0.7414551973342896, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/1c0d7f87ca89369224409fa44c6b9c4917616f846c108e06af2ab1a028eacdac.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "1c578c8ffeda4190e589f1f994f7156729e9ee235f269442e3a8f5fac6c85b98", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "41128e42a7d6b4acc1e1091bb8290e79d15551d36c861ed97e72b93447fdcf7d", "generation_seconds_batch": 20.507730351993814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13917052745819092, "target_z": -0.16992187215058202, "ce": 6.046441555023193, "genuineness": 4.281409740447998, "identity": 0.7514377236366272, "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_Disgust/1c578c8ffeda4190e589f1f994f7156729e9ee235f269442e3a8f5fac6c85b98.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "1c794f7b68b0c43ccfa6b3d760a95c13c0a66a1603de4a400387bab41c82abef", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ba58e7c08c50655fc97e5a4c78cb7036cd0e100f00c4e1e6e78606453078e06d", "generation_seconds_batch": 18.78386472002603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07022632658481598, "target_z": -0.3105468645521341, "ce": 6.229123115539551, "genuineness": 3.9173994064331055, "identity": 0.3069084584712982, "hypothesis": "The 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_Disgust/1c794f7b68b0c43ccfa6b3d760a95c13c0a66a1603de4a400387bab41c82abef.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "1c7ae89509fb6277e8f5c5e8ac34a03985ab5480b918fbba1cb149853eb5d675", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "015e79836b24e261ed594a9d520eb5a388d7776870381179c09315399da3a055", "generation_seconds_batch": 18.882588249980472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48484909534454346, "target_z": 0.5351562253050443, "ce": 5.760505676269531, "genuineness": 3.973883628845215, "identity": 0.46748271584510803, "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_Disgust/1c7ae89509fb6277e8f5c5e8ac34a03985ab5480b918fbba1cb149853eb5d675.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "1c92d365100c3d6c16667bcca399d88d5bf7661d59d8314bfc1b8bf01640cd52", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f5f71c7b7ac891845a6029e85c6b3c01f53c7e9aecf90bc1ac3b19638b1dd64e", "generation_seconds_batch": 14.133002788992599, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08746236562728882, "target_z": -0.27539063924708984, "ce": 6.141753673553467, "genuineness": 3.8295347690582275, "identity": 0.4829728901386261, "hypothesis": "The 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_Disgust/1c92d365100c3d6c16667bcca399d88d5bf7661d59d8314bfc1b8bf01640cd52.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "1cf8192b6a03683e2fc4ad773b4ed0e434c74d84568e57e6fbf5ff88c91daf8a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "90fe8a0cec1be090e34d3e738f5e681d99129b61f1f2220fee9fe33c5a294847", "generation_seconds_batch": 13.966939782025293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.022656843066215515, "target_z": -0.5, "ce": 6.125868320465088, "genuineness": 4.2374773025512695, "identity": 0.6804933547973633, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/1cf8192b6a03683e2fc4ad773b4ed0e434c74d84568e57e6fbf5ff88c91daf8a.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "1d10aa5f93c0d8d90aea61217d4d65d244705b2a5faf58fcc0f280d7677ffb96", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "2d364e04e76239468731f1e46f0a3e76cff4fbb6595e036509bd2f2de6715d5c", "generation_seconds_batch": 19.353109369054437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03606267273426056, "target_z": -0.5273437746949557, "ce": 6.24500846862793, "genuineness": 4.369274139404297, "identity": 0.765583336353302, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/1d10aa5f93c0d8d90aea61217d4d65d244705b2a5faf58fcc0f280d7677ffb96.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "1d11ad8aa4ace26b766a583ee897bee24fd5f1d57b5512720c6d3b01361b7051", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0200f391a02c998669f1561e2c31e3ef1c0e4467a616070b1d261b7f493767b7", "generation_seconds_batch": 20.16963824001141, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12576469779014587, "target_z": -0.19726564684553777, "ce": 6.427689552307129, "genuineness": 4.444586753845215, "identity": 0.5193657279014587, "hypothesis": "Die Tür 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_Disgust/1d11ad8aa4ace26b766a583ee897bee24fd5f1d57b5512720c6d3b01361b7051.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "1d2d7ebed4b3faebcce45e8f82e25aba64597c0ce1d16eb68baba92283eedece", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7afbf1f2b41c35dd490606e6610b08dc49047a0ec92903088477677946c82df9", "generation_seconds_batch": 18.968429408967495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.08394058048725128, "target_z": -0.625, "ce": 6.340320587158203, "genuineness": 4.306513786315918, "identity": 0.5529415607452393, "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_Disgust/1d2d7ebed4b3faebcce45e8f82e25aba64597c0ce1d16eb68baba92283eedece.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "1d32ff0d9bf73f2a3a1c04a6430ff2f811daa834dba24d06df297e5f3407e9b6", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6155a076044f18535729fc397e37e8d039c041df4a5682b5e2e32eb4e0d59d4a", "generation_seconds_batch": 18.881560999085195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.046287357807159424, "target_z": -0.3593750075984479, "ce": 5.959072113037109, "genuineness": 4.168440818786621, "identity": 0.6276392936706543, "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_Disgust/1d32ff0d9bf73f2a3a1c04a6430ff2f811daa834dba24d06df297e5f3407e9b6.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "490db5311134435d6fe0222f91e2d8a104bdc8d189c9b1ce8fd02d5f01dcb240", "generation_seconds_batch": 13.625426889047958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.046287357807159424, "target_z": -0.3593750075984479, "ce": 6.308549880981445, "genuineness": 4.494794845581055, "identity": 0.6383156776428223, "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_Disgust/1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3.mp3" }, { "id": "heldout-de-1", "language": "de", "sentences": [ "Die Schlüssel liegen auf dem Küchentisch.", "Ich suchte in der Schublade... dann neben dem Fenster.", "Nimm sie mit, wenn du gehst." ], "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-1", "key": "1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "d0bd330160e1cfc4da3ac4f062199e7d79a0e381ac71c695846c94d737c0cac7", "generation_seconds_batch": 13.671590057900175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04437224566936493, "target_z": -0.36328124810038803, "ce": 6.284721851348877, "genuineness": 4.375550270080566, "identity": 0.5991778373718262, "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_Disgust/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "4a4b0630349ea36362f93e25b4f8e15825185de5fa0cff65e13ea14f773abcc3", "generation_seconds_batch": 13.625426889047958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007985025644302368, "target_z": -0.4375, "ce": 6.2767791748046875, "genuineness": 4.394378662109375, "identity": 0.6876777410507202, "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_Disgust/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "1ec3830dde4cd40137ff2e3e6e3192c0d0cbd71b64df5cdad1a2cb93f0bd1806", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "796845256f56f051ea26e9b3faec06084af4339c86a1e4c406e9900980781fc5", "generation_seconds_batch": 19.37031012494117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07022632658481598, "target_z": -0.3105468645521341, "ce": 6.117925643920898, "genuineness": 4.425758361816406, "identity": 0.5994174480438232, "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_Disgust/1ec3830dde4cd40137ff2e3e6e3192c0d0cbd71b64df5cdad1a2cb93f0bd1806.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "1f22fba024aa860e71432cc72d0138ded9d1ddfd5dd2f9b043b341e729715ae7", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8149561874b9268163b8d431e23b7544cabac3f908abbfb2c7c534443a336318", "generation_seconds_batch": 21.06154018698726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7740316987037659, "target_z": 1.1249999088186249, "ce": 6.157639026641846, "genuineness": 4.017816066741943, "identity": 0.5654560327529907, "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_Disgust/1f22fba024aa860e71432cc72d0138ded9d1ddfd5dd2f9b043b341e729715ae7.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": "1fc67a6db44819a219f529b49e366bbe7ec6bebbda2773d8a9162df4c5c8670b", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8b997f17e4c184b6ed83b47f704368743d977920183a3cf5c507c0d2a0c4325d", "generation_seconds_batch": 14.52495331200771, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11906179785728455, "target_z": -0.21093750379922396, "ce": 6.1020402908325195, "genuineness": 4.369274139404297, "identity": 0.6130304932594299, "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_Disgust/1fc67a6db44819a219f529b49e366bbe7ec6bebbda2773d8a9162df4c5c8670b.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "1fc7795969482ba4ce9cc0b1932f9582d46055061b6426f9e3fbd8dbf3a97388", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "022feac2590f6a9598ad8e16e476a4a0547338c7815fb107eeaa1447729864bd", "generation_seconds_batch": 21.79756683600135, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27801650762557983, "target_z": 0.11328127849417971, "ce": 6.229123115539551, "genuineness": 4.068024158477783, "identity": 0.4626094102859497, "hypothesis": "Ik heb het klein doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/1fc7795969482ba4ce9cc0b1932f9582d46055061b6426f9e3fbd8dbf3a97388.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": "202c27508bdd5a70ddeea424a8c9be8c4a49798f6c5c47a8d7817dd1ae08048e", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a7c7d16fc048347787b00fcdea90902b31fa37dd1ff81beb8d15ec5b36d39dc4", "generation_seconds_batch": 13.674361295998096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.98438560962677, "target_z": 3.593750106378271, "ce": 6.221180438995361, "genuineness": 3.722842216491699, "identity": 0.14800575375556946, "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_Disgust/202c27508bdd5a70ddeea424a8c9be8c4a49798f6c5c47a8d7817dd1ae08048e.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "203e7dbb5e8d7c8ecc771665b928b895a4e3beddaf3f4e90fcd18caf654b5e91", "bucket": "emo_Disgust", "phase": "wording", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "26dd74816d0699daf595dd4a03951f98227169a1efcd1607d444e3613bc07f0a", "generation_seconds_batch": 14.106234717997722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009900137782096863, "target_z": -0.4335937594980599, "ce": 6.1894097328186035, "genuineness": 4.6203155517578125, "identity": 0.7162879109382629, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/203e7dbb5e8d7c8ecc771665b928b895a4e3beddaf3f4e90fcd18caf654b5e91.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": "2099b52c83bb125d54ac7e2f67d7472bdaba048233290c2732bcb76dae8c5adb", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3b5f47951c1431dc4069eb3489bc96e32a6282115488dcbdb1b37e103247c207", "generation_seconds_batch": 18.71268640004564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030008867383003235, "target_z": -0.392578127849418, "ce": 6.070269584655762, "genuineness": 3.8295347690582275, "identity": 0.26771149039268494, "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_Disgust/2099b52c83bb125d54ac7e2f67d7472bdaba048233290c2732bcb76dae8c5adb.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "20b70952c28585c07c40a12822063e757fd5b8ed507cecebbfe4d99f2857db72", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "23d725e128ac8e018238a1206dcc2281b9929bc5ed349d9243d9ce41b5c38261", "generation_seconds_batch": 18.58229629904963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5400785207748413, "target_z": 2.687500121575167, "ce": 5.534139156341553, "genuineness": 3.5439748764038086, "identity": 0.5580849647521973, "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_Disgust/20b70952c28585c07c40a12822063e757fd5b8ed507cecebbfe4d99f2857db72.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "20ff7c47f24e9061d62d41d66dd21e561dffe622b0c3cd03100e489f1db23466", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "7b987b6031fd1476c7793ea09b8422c4dcd16fe9e31a61af3ecf1557053df8e2", "generation_seconds_batch": 19.078272970044054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15449145436286926, "target_z": -0.13867188734747787, "ce": 6.213237762451172, "genuineness": 4.137060642242432, "identity": 0.7255631685256958, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/20ff7c47f24e9061d62d41d66dd21e561dffe622b0c3cd03100e489f1db23466.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "2101371d99587e847479a8ed2ca97023b38b6463af41b9cce07a558c65d5d901", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "066b6c96df77682ebe14b9fee3abb3fd17f0e8a9c86069d4d0966b2df0259195", "generation_seconds_batch": 15.327921935007907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08267457783222198, "target_z": -0.28515625569883596, "ce": 6.038498878479004, "genuineness": 4.017816066741943, "identity": 0.6633366346359253, "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_Disgust/2101371d99587e847479a8ed2ca97023b38b6463af41b9cce07a558c65d5d901.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": "2178dd78961a08c5bca7df68dfeb9695dc2ccb6c425483894bd9506e53ed513f", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4d53295575f860efe0efa808d8708e8f223454594010ad075714ef9eb407b60b", "generation_seconds_batch": 13.695897464989685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06160829961299896, "target_z": -0.3281249924015521, "ce": 6.070269584655762, "genuineness": 4.406930446624756, "identity": 0.6276152729988098, "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_Disgust/2178dd78961a08c5bca7df68dfeb9695dc2ccb6c425483894bd9506e53ed513f.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "2183087044968f0a1356f2795585d703e6c44a8ee5a44d497ca7c493c4373203", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "b06938ca98bf95dd5e53574120afffd2c97afad39df5de61860582b1a6a1838e", "generation_seconds_batch": 20.00499614002183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03223241865634918, "target_z": -0.5195312329034921, "ce": 6.41180419921875, "genuineness": 4.507347106933594, "identity": 0.6830693483352661, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/2183087044968f0a1356f2795585d703e6c44a8ee5a44d497ca7c493c4373203.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": "219a97fbbd35c5a13c4548a1a1b71be484f7e54f57a73a86da620d309a4a64d3", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f3c742f68277aa502cb59cb4804312dd54a9b36883ba308b1f64a9e5f386a74a", "generation_seconds_batch": 13.608083826024085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1991876363754272, "target_z": 1.9921874278147447, "ce": 6.117925643920898, "genuineness": 3.8420867919921875, "identity": 0.3748728036880493, "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_Disgust/219a97fbbd35c5a13c4548a1a1b71be484f7e54f57a73a86da620d309a4a64d3.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "21f6b590815289cd75922305fb555341f911e21b410adcf2f70eb5ec710bc830", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5f1da7c093fa36cc025808ed26b63380761ac92e0da6eade1fd5389a047f83b2", "generation_seconds_batch": 15.97963591804728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10757109522819519, "target_z": -0.23437500759844793, "ce": 6.316492557525635, "genuineness": 4.331617832183838, "identity": 0.3842277228832245, "hypothesis": "Die Tür 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_Disgust/21f6b590815289cd75922305fb555341f911e21b410adcf2f70eb5ec710bc830.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "21fc550fa72b39aefaec4ab1501f67f202e0183a8036e2f443cf1c41baff0aea", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2428805b66dc2fc4b4f1b1932cae8d8fb0c3d069294636824ebc1cee32a518ca", "generation_seconds_batch": 19.07437884400133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08075946569442749, "target_z": -0.28906249620077606, "ce": 6.213237762451172, "genuineness": 4.507347106933594, "identity": 0.8080686330795288, "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_Disgust/21fc550fa72b39aefaec4ab1501f67f202e0183a8036e2f443cf1c41baff0aea.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "2205195a8f3bf3a944ecb91d72fe47af3b66623174a495fab985a7aa542384ff", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "77d4ba0b59fbd086382882fc3e21d5469fcb31c9f35742e113369fce59d272d2", "generation_seconds_batch": 22.18224699201528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.047553375363349915, "target_z": -0.5507812784941797, "ce": 6.300607204437256, "genuineness": 4.3504462242126465, "identity": 0.36903083324432373, "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_Disgust/2205195a8f3bf3a944ecb91d72fe47af3b66623174a495fab985a7aa542384ff.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": "22589f0f47047b00d74cb023e52d3fe7ae398e8930b1c42d6934d1d92308bc5b", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "068331855f36874f474c7f9bdc877f5f22ac586de4c3d39f7940ba7a06338244", "generation_seconds_batch": 13.593758465955034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09608039259910583, "target_z": -0.25781251139767186, "ce": 6.252951145172119, "genuineness": 4.042920112609863, "identity": 0.7428046464920044, "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_Disgust/22589f0f47047b00d74cb023e52d3fe7ae398e8930b1c42d6934d1d92308bc5b.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "22743d64094a254e98ca084a8cd0473c31134999a821f20bf6197495c6543dd3", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "347c5c10f71e6d50e6e03b3251df3077d6be0e525b456d41b2f82de2161f7d2e", "generation_seconds_batch": 21.717241630074568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10852865874767303, "target_z": -0.23242187215058202, "ce": 6.324435234069824, "genuineness": 4.632867813110352, "identity": 0.6489728689193726, "hypothesis": "Die Tür 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_Disgust/22743d64094a254e98ca084a8cd0473c31134999a821f20bf6197495c6543dd3.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "22a145f9ae992635f747a76dbc27649771c2bed1329c63fdb17911046628d52e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d8dd8416b2076b47aa1bd32a1770d7e4b88320fe833ba43ffb29b75ba80eec35", "generation_seconds_batch": 20.543687414028682, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055862948298454285, "target_z": -0.33984374430116404, "ce": 6.086154937744141, "genuineness": 3.6914620399475098, "identity": 0.41834473609924316, "hypothesis": "The 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_Disgust/22a145f9ae992635f747a76dbc27649771c2bed1329c63fdb17911046628d52e.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "23317b4e98cd375f82d6b97e5120843927d5df06e3393e78031ce0e1eb856a6b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "43dd5f289f9b1aff2f4952bde39b21d930842489f055f7119a8b1719d5b00409", "generation_seconds_batch": 18.84440712898504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08841992914676666, "target_z": -0.27343750379922394, "ce": 6.340320587158203, "genuineness": 4.7081804275512695, "identity": 0.5722196102142334, "hypothesis": "Die Tür 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_Disgust/23317b4e98cd375f82d6b97e5120843927d5df06e3393e78031ce0e1eb856a6b.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "23574d279685eb474c1f87fedb781142105d098d72d10d336913abbd42f3d555", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a2dede595a7501caa9cbb093979f57cdc86fb1d1cbbca75cc4b024720683441d", "generation_seconds_batch": 18.860652763978578, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09512284398078918, "target_z": -0.25976561645174606, "ce": 6.1894097328186035, "genuineness": 4.080576419830322, "identity": 0.4123753309249878, "hypothesis": "The 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_Disgust/23574d279685eb474c1f87fedb781142105d098d72d10d336913abbd42f3d555.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "2397abc3b8455537221e056c2f8bc39e0628c228faa3606f621448886e77ac58", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6f1a21e32be381bf9a0505914c49c2d446355e1740ccfb95a3a205957dd3dc15", "generation_seconds_batch": 18.95612774603069, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16023680567741394, "target_z": -0.1269531354478659, "ce": 6.173524379730225, "genuineness": 4.061748504638672, "identity": -0.0015059113502502441, "hypothesis": "The 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_Disgust/2397abc3b8455537221e056c2f8bc39e0628c228faa3606f621448886e77ac58.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "23bab3a0b137d2d2bdff4deb6ab32a4bdcac736d79a4d637ab5a87af8436237f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "2035467677b8e8ae934c5ce1b3280f24a7ef884802a7f929675e54b4198117a8", "generation_seconds_batch": 19.984008742962033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0252210795879364, "target_z": -0.40234374430116404, "ce": 5.276002407073975, "genuineness": 4.005263805389404, "identity": 0.5743775963783264, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre, nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/23bab3a0b137d2d2bdff4deb6ab32a4bdcac736d79a4d637ab5a87af8436237f.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "242cdeb61a81bd3afea393c2a66da90e55615f3dc9697569d39f1314b378b6d2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a0f4211cb4cfafbe48f821b22be23c71c1eeb54c3b36dcdf1b5c1f55da99cdf5", "generation_seconds_batch": 18.958396796952, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.014038816094398499, "target_z": -0.482421872150582, "ce": 6.4515180587768555, "genuineness": 4.20609712600708, "identity": 0.6130197048187256, "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_Disgust/242cdeb61a81bd3afea393c2a66da90e55615f3dc9697569d39f1314b378b6d2.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": "2534b4a5e17f45bc4049d752a1dfbda17580be54f06d302e02a1207dfe80548b", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f2fee087ae38120f71731865ddc86e70be2f7ca7c1636ca7f6d7514bc04c6106", "generation_seconds_batch": 13.616183253005147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055862948298454285, "target_z": -0.33984374430116404, "ce": 5.418970584869385, "genuineness": 3.9425034523010254, "identity": 0.7113137245178223, "hypothesis": "La route tourne à gauche après le pont, continue jusqu'à la petite barrière en bois. J't'entrée de l'autre côté.", "wer": 0.1, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/2534b4a5e17f45bc4049d752a1dfbda17580be54f06d302e02a1207dfe80548b.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "2536e0a63cad34521410f63051006315380a626bf0e3c473f40e507469663a3b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7676c6ed42d0866162814bc8bef673700df696046dc59ba566f08c8343c45b1c", "generation_seconds_batch": 21.014618846937083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3715481758117676, "target_z": 2.3437499848031043, "ce": 5.831989288330078, "genuineness": 3.6475296020507812, "identity": 0.5161424875259399, "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_Disgust/2536e0a63cad34521410f63051006315380a626bf0e3c473f40e507469663a3b.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "255225bfc33bef9fbbe23d640c99a8eba64c7c59ea9a732f041fd92efbe97132", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "141539fff6aecea86a9eed91381882dfb21f28c7df4abe551a2b2cd8e57c131d", "generation_seconds_batch": 18.881560999085195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09225016832351685, "target_z": -0.2656249924015521, "ce": 5.935244083404541, "genuineness": 4.494794845581055, "identity": 0.5192503929138184, "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_Disgust/255225bfc33bef9fbbe23d640c99a8eba64c7c59ea9a732f041fd92efbe97132.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "25635c0de419e269eb61f9c596b1582b40bdbfd83e62817d1e69bf04b11ed756", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "464b6e7b8056f70e39e6097a9f1e74c0f0c8dedeb01a3a79d47cb2db8d1e0025", "generation_seconds_batch": 20.83774839004036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05107516050338745, "target_z": -0.34960936075291016, "ce": 6.284721851348877, "genuineness": 4.024092197418213, "identity": 0.7759384512901306, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/25635c0de419e269eb61f9c596b1582b40bdbfd83e62817d1e69bf04b11ed756.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "256e68b8920f25be2a99d62f5456f497c7cb4b449f887ed2cf770c8eb1eebf22", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2513e2bf17e8b9fbb7a7cc98fa6033e6ad2d9f5393bd5d614eb8bcd9049b0e1a", "generation_seconds_batch": 15.931227068067528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.005420789122581482, "target_z": -0.46484374430116404, "ce": 6.0305562019348145, "genuineness": 4.457139015197754, "identity": 0.6216393113136292, "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_Disgust/256e68b8920f25be2a99d62f5456f497c7cb4b449f887ed2cf770c8eb1eebf22.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "2574362c5c69c9b3b74039fe18ae1f42df382002574086bda8185b7e9666e984", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d2213b4ba825ca8093b9253b2a743d6747e46d5fdbc12186797cf538ffd65f5d", "generation_seconds_batch": 18.927668135031126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1678972840309143, "target_z": -0.11132811265252213, "ce": 6.300607204437256, "genuineness": 4.444586753845215, "identity": 0.32405710220336914, "hypothesis": "Die Tür 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_Disgust/2574362c5c69c9b3b74039fe18ae1f42df382002574086bda8185b7e9666e984.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": "2695be462b3bd8bade8c23383b502c49145d1c1a2a51321e9e64d854391baf02", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "400a8df3825a75011e5d4e43d2a862c0d997154e9565461acf88b58fe6c3895f", "generation_seconds_batch": 19.034079334931448, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6706154346466064, "target_z": 0.9140624962007761, "ce": 5.011908531188965, "genuineness": 3.7542223930358887, "identity": 0.5609501600265503, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suche in der Schublade. Daneben dem Fenster. Nimm sie mit, wenn du gehst!", "wer": 0.14285714285714285, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/2695be462b3bd8bade8c23383b502c49145d1c1a2a51321e9e64d854391baf02.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "26ba69b67ef3769cbac7e4714b5f5e37ff4026982db94ad093f1017b2d49a2c1", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "674ddcc8e681c2e60d3b8f4d17fd1efd95d3a7d64042207d2525be753d00b3cd", "generation_seconds_batch": 18.99189424503129, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.045638248324394226, "target_z": -0.5468750075984479, "ce": 6.3641486167907715, "genuineness": 4.162164688110352, "identity": 0.39302390813827515, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/26ba69b67ef3769cbac7e4714b5f5e37ff4026982db94ad093f1017b2d49a2c1.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "26c612a33c368aa3a88184568b1268473ad4bb136a47b66e42d049f725d820da", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "8105ccebcf7a8588bc7208b6723f291f17e1d03324a37cf593b4db8a74f8463b", "generation_seconds_batch": 19.014376088045537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38143280148506165, "target_z": 0.32421875189961197, "ce": 5.974957466125488, "genuineness": 3.8169827461242676, "identity": 0.409887433052063, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/26c612a33c368aa3a88184568b1268473ad4bb136a47b66e42d049f725d820da.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "f02fb4e1f87e9f99456487fc2fed125a1f63f855d908b1ca9370300a3a1980d3", "generation_seconds_batch": 15.037744753062725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023305967450141907, "target_z": -0.40624998480310415, "ce": 6.427689552307129, "genuineness": 4.457139015197754, "identity": 0.2235221415758133, "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_Disgust/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "27727142d376a973ce2fd339297ff96cb3fdc3e78c6c14d6c538274303cfeb66", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cd16e0dc3c92e9ffd3fcc29316fafa2bb86e5e127a69885a39a1735f76a19b30", "generation_seconds_batch": 19.56028770795092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06352341175079346, "target_z": -0.32421875189961197, "ce": 6.070269584655762, "genuineness": 4.118232727050781, "identity": 0.4551098644733429, "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_Disgust/27727142d376a973ce2fd339297ff96cb3fdc3e78c6c14d6c538274303cfeb66.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "27a66c19492eb304c9fb25d313247fac3a139f7ca3d0fdcbda0dd1df12d501be", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "88343cdfc809fabaa7ae1d4727ace3cae3eb94d374ad7077e20d67a8ba56a968", "generation_seconds_batch": 21.998380220960826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08458970487117767, "target_z": -0.28124998480310415, "ce": 6.173524379730225, "genuineness": 4.049196243286133, "identity": 0.5373942852020264, "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_Disgust/27a66c19492eb304c9fb25d313247fac3a139f7ca3d0fdcbda0dd1df12d501be.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": "27bba919c27ce0ea3004730aeb4d10b2e67a6e2d421d84148e4f5e0856e0b708", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Someone moved the little blue chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "f8a42d46ee14f7c53d8249246e6d9b44687890a1ffc83234663dbeb165ef0385", "generation_seconds_batch": 15.270441215019673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05107516050338745, "target_z": -0.34960936075291016, "ce": 6.24500846862793, "genuineness": 3.6789097785949707, "identity": 0.4057053327560425, "hypothesis": "Someone moved the little blue chair. It used to stand here. Beside the tall bookshelf. We can put it back after lunch.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/27bba919c27ce0ea3004730aeb4d10b2e67a6e2d421d84148e4f5e0856e0b708.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": "27ff9137d82e0c95a610d87a958720f11a2284bdee40b85386a962d22b25beb2", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7022443808cea720bc692f52aeb2376af20c7c67e93eaf361cdc599daedb7577", "generation_seconds_batch": 13.695897464989685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08554725348949432, "target_z": -0.27929687974902995, "ce": 5.967014789581299, "genuineness": 4.507347106933594, "identity": 0.8149998784065247, "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_Disgust/27ff9137d82e0c95a610d87a958720f11a2284bdee40b85386a962d22b25beb2.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "282364ae5cfc18b640fe765b371f4a2ab4b33aa5e85ee854cab423b6405ce4c1", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "79d186fd38366629ef929b3c6a5da0b3758861c4ba6f90954c3bfcbafc6ca1d7", "generation_seconds_batch": 18.80373373196926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.049468472599983215, "target_z": -0.5546874886023281, "ce": 6.443574905395508, "genuineness": 4.545003414154053, "identity": 0.1912684142589569, "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_Disgust/282364ae5cfc18b640fe765b371f4a2ab4b33aa5e85ee854cab423b6405ce4c1.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": "28b96747debdb6c0cc2bf07ce0a7dc0eb2014f36bf413c07fcd505311f05d5a2", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6a7b3d533816f2d4f821e7348b9e2330ae02e8965e7b749e796be4582edd4222", "generation_seconds_batch": 13.644421658013016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2215205430984497, "target_z": -0.001953135447865894, "ce": 6.197352409362793, "genuineness": 4.18099308013916, "identity": 0.5806566476821899, "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_Disgust/28b96747debdb6c0cc2bf07ce0a7dc0eb2014f36bf413c07fcd505311f05d5a2.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "2929124cec05e66a72dd2766029dd3924ce2b1b0b4712282ed183ceaab074f02", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "68043a301771ab5ef4fa00d73d90f9f584a01b8b06bb6677586d4ec335198b09", "generation_seconds_batch": 19.66788887907751, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10757109522819519, "target_z": -0.23437500759844793, "ce": 6.022613525390625, "genuineness": 4.362998008728027, "identity": 0.4487901031970978, "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_Disgust/2929124cec05e66a72dd2766029dd3924ce2b1b0b4712282ed183ceaab074f02.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": "293bab94269b3eba4bb0398b629ee4964d554ea48e7e1dc3601b2298a9b5f12c", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "479715c3edd412a626b7c116354ed515568c249a4842d54056e8afb64371673d", "generation_seconds_batch": 13.635724282939918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9425619840621948, "target_z": 1.4687499240155208, "ce": 6.070269584655762, "genuineness": 3.9927117824554443, "identity": 0.6456859111785889, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade. Daneben dem Fenster. Nimm sie mit, wenn du gehst!", "wer": 0.09523809523809523, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/293bab94269b3eba4bb0398b629ee4964d554ea48e7e1dc3601b2298a9b5f12c.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "2967dffbc19e598612e12c9423b8827eb1c5e0223e2344c27a8c0369c5fc7338", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "eac877e715f6f9128ec5a9ef714ea9f56139bdec7497708b69b0c2ddb0b8b262", "generation_seconds_batch": 18.69262325402815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.078844353556633, "target_z": -0.2929687367027161, "ce": 6.284721851348877, "genuineness": 4.582659721374512, "identity": 0.8144765496253967, "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_Disgust/2967dffbc19e598612e12c9423b8827eb1c5e0223e2344c27a8c0369c5fc7338.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "297eb18ae3d5560097f7150d465f1dd0ee4accd177dcd0c3cf2a8e4370e866d6", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9e001871c30db5e75bfeef29242244c9e6a6d32fb2a95060524f57b05bb33164", "generation_seconds_batch": 18.60438604198862, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1835577487945557, "target_z": 4.000000091181375, "ce": 6.149696350097656, "genuineness": 3.7040140628814697, "identity": 0.6404680013656616, "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_Disgust/297eb18ae3d5560097f7150d465f1dd0ee4accd177dcd0c3cf2a8e4370e866d6.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": "29fd9430a64c29b782fda93fc1a07d2ec318f3a20dd067c81f88aa7e3e661648", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The keys are on the kitchen table.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d9270e49fb219229744486613930ca8cc9755cfb527e34e895ce1d0afd4f598d", "generation_seconds_batch": 15.1254305629991, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.091292604804039, "target_z": -0.267578127849418, "ce": 6.268836498260498, "genuineness": 3.7542223930358887, "identity": 0.48285365104675293, "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_Disgust/29fd9430a64c29b782fda93fc1a07d2ec318f3a20dd067c81f88aa7e3e661648.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": "2a50975852d433e0d7c1c89b2e924e66ca7a54e7819176b0a55149d451a7729e", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Escribí el número en el sobre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "76bcf191c7b2a2c4bd55ddb45f0b47ec9dffbde4ca115d552d8ee3d4e76352d9", "generation_seconds_batch": 13.709977115970105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24545951187610626, "target_z": 0.04687500759844792, "ce": 6.197352409362793, "genuineness": 3.9927117824554443, "identity": 0.5852903127670288, "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": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/2a50975852d433e0d7c1c89b2e924e66ca7a54e7819176b0a55149d451a7729e.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "2a7c1f90758aafab37c9b2e76c4488538b47e5145065707e8a855fef1cc75206", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1866908d2cc1ece7dd7a02c7f996f4b357b1fd8886de534f07db13aaae1d0909", "generation_seconds_batch": 20.507730351993814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09225016832351685, "target_z": -0.2656249924015521, "ce": 5.839932441711426, "genuineness": 4.243753433227539, "identity": 0.6669692993164062, "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_Disgust/2a7c1f90758aafab37c9b2e76c4488538b47e5145065707e8a855fef1cc75206.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": "2a7f1b1b78b695d498ad01b594b9b6980a28adfebaa17519bee197ed62fd093f", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The road turns left behind the bridge.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1eb380e1c0f6688999f5c093e5f002e62201c952714ba66b45d4e70705a64391", "generation_seconds_batch": 18.694081041030586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8697875738143921, "target_z": 1.3203124810038802, "ce": 6.221180438995361, "genuineness": 3.3243136405944824, "identity": 0.21534571051597595, "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_Disgust/2a7f1b1b78b695d498ad01b594b9b6980a28adfebaa17519bee197ed62fd093f.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "2b36adaee26baf1e7c38194f3c1f1b0f5b595e8cca911714ee0734f0a1768c08", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8611e0ee93635f00a6de75216dc53281a18d9478a3c86cac3e52b9e0dce5787e", "generation_seconds_batch": 19.035920615075156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.07436500489711761, "target_z": -0.6054687670965079, "ce": 6.340320587158203, "genuineness": 4.18726921081543, "identity": 0.4704523980617523, "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_Disgust/2b36adaee26baf1e7c38194f3c1f1b0f5b595e8cca911714ee0734f0a1768c08.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "2b8a5e53477dc3945b2585b7dd94ff3596d519e0a152b35c74c628337293e75d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "599e4e460ee8947ab666cfed60db2db1e7c5b3da1e2a08717712ee8cb92ad30f", "generation_seconds_batch": 19.837828695075586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.06670452654361725, "target_z": -0.589843744301164, "ce": 6.523001670837402, "genuineness": 4.720732688903809, "identity": 0.3598262369632721, "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_Disgust/2b8a5e53477dc3945b2585b7dd94ff3596d519e0a152b35c74c628337293e75d.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "2c009a542ec477fb3e14ae941712e4419070c179b6e58831a477cb54bf25001a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f799b8a86fad0a5154023b4a1c63c2bd901f1c78c44c2e461a6c4980c8957af6", "generation_seconds_batch": 21.64526493300218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06352341175079346, "target_z": -0.32421875189961197, "ce": 5.982900142669678, "genuineness": 4.293961524963379, "identity": 0.6630358695983887, "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_Disgust/2c009a542ec477fb3e14ae941712e4419070c179b6e58831a477cb54bf25001a.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "2c6e1f2df8a1fd7059311f6b078df7c4be418745092e6cb25e0ad6781953b246", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f07fb6950bd6f1fb795066896055a988c6e4938c5653f780b878991af9e22a05", "generation_seconds_batch": 15.088876342051663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12097691744565964, "target_z": -0.20703124810038803, "ce": 5.732706069946289, "genuineness": 4.306513786315918, "identity": 0.6400697827339172, "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_Disgust/2c6e1f2df8a1fd7059311f6b078df7c4be418745092e6cb25e0ad6781953b246.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "2c7f30a4869d41db26139eebc736d50bdee0f0323a7a6dd3151c75c03daceefa", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "75a57502376b4b03b0e75a44e04dc08f2378b6c98a0d7966cac82133f2310305", "generation_seconds_batch": 20.0280799070606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.028402194380760193, "target_z": -0.511718751899612, "ce": 5.855817794799805, "genuineness": 4.381826400756836, "identity": 0.44030219316482544, "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_Disgust/2c7f30a4869d41db26139eebc736d50bdee0f0323a7a6dd3151c75c03daceefa.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": "2cce2b52c39badedf3711541527c3dd7dbf95f69ebb30aa401f022595646ec4b", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b02c6b843d0aca8a789901028e1e6e48f6733e71a7f429a36ee2dbc6f50b2f46", "generation_seconds_batch": 18.540502244024538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16598215699195862, "target_z": -0.11523438354825391, "ce": 6.141753673553467, "genuineness": 3.7040140628814697, "identity": 0.627550482749939, "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_Disgust/2cce2b52c39badedf3711541527c3dd7dbf95f69ebb30aa401f022595646ec4b.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "2ccfa34c8aa153965a9af3d0404ee676c34492d6985164fe5397e1a75a3a437d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "95b1b10d7947924242f87b57d41de1b35573fba11c3cdd5df5c050ee24680ef5", "generation_seconds_batch": 21.64526493300218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13534030318260193, "target_z": -0.17773435315446223, "ce": 6.062326908111572, "genuineness": 4.281409740447998, "identity": 0.6612677574157715, "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_Disgust/2ccfa34c8aa153965a9af3d0404ee676c34492d6985164fe5397e1a75a3a437d.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "2ce438637fb722f55d774970526d94421d21546ccacb1ee016221484f7872957", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2132df977928fcb001a3fe631297feed3f0136f5f1d1d6275fdac6e7fbaf6aad", "generation_seconds_batch": 21.79756683600135, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1181042417883873, "target_z": -0.21289062405019402, "ce": 6.205295085906982, "genuineness": 3.9801597595214844, "identity": 0.5488829612731934, "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_Disgust/2ce438637fb722f55d774970526d94421d21546ccacb1ee016221484f7872957.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "2cecd1c70acb757ee4227f6a7d039af6bc4c65b40c545b632e1fe5615af1a29d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9c3794c62ab8fdffc2e22e82d375e84744278d1ee5e536e1c57ca9438fc166b0", "generation_seconds_batch": 18.72614193696063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02169927954673767, "target_z": -0.4980468645521341, "ce": 6.070269584655762, "genuineness": 4.532451152801514, "identity": 0.7338589429855347, "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_Disgust/2cecd1c70acb757ee4227f6a7d039af6bc4c65b40c545b632e1fe5615af1a29d.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "2d209ae2f41e08ac73e583874effe11f50add520fff9088390a750e6a0704efb", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1628c1f880f1f3712de39278109199c12aecc786b77758a33716733c9ec833f3", "generation_seconds_batch": 18.980662252986804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.059693172574043274, "target_z": -0.3320312632972839, "ce": 6.133810997009277, "genuineness": 4.356721878051758, "identity": 0.49409642815589905, "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_Disgust/2d209ae2f41e08ac73e583874effe11f50add520fff9088390a750e6a0704efb.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "2d36cc05386c6857b8576ebea0e74faebbc509d5036e98b982c58c29f51c3ecc", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "564d6dfcfb9c951ae56f68c2f0e59dca8718ef9c0bbaba278c84d29c3223a43c", "generation_seconds_batch": 21.344437616993673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04916003346443176, "target_z": -0.3535156316486419, "ce": 6.205295085906982, "genuineness": 4.18099308013916, "identity": 0.2663653790950775, "hypothesis": "The 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_Disgust/2d36cc05386c6857b8576ebea0e74faebbc509d5036e98b982c58c29f51c3ecc.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": "2d3cc402f12087e482300c3d447efd88fa12d0895b5f13249022acac6a8d4eb1", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8c1a8bbb63f5409250590592435a7ad365af6d9f1ba3053be878d7ff1286641e", "generation_seconds_batch": 13.575326486025006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09033504128456116, "target_z": -0.2695312632972839, "ce": 5.546053409576416, "genuineness": 4.005263805389404, "identity": 0.5790703892707825, "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_Disgust/2d3cc402f12087e482300c3d447efd88fa12d0895b5f13249022acac6a8d4eb1.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "2d53ac58dcee29c5a62f1799968d5d06e4d9b711e9ccb62fbf9a2ba442f8aa9b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "aa8e012686677f6f54496efe371b7e4059131b141cf6d8cb0ba1170b3aba1bdd", "generation_seconds_batch": 13.682297415100038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.014996379613876343, "target_z": -0.4843750075984479, "ce": 6.268836498260498, "genuineness": 4.582659721374512, "identity": 0.6718138456344604, "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_Disgust/2d53ac58dcee29c5a62f1799968d5d06e4d9b711e9ccb62fbf9a2ba442f8aa9b.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "2d68d9e17d65ae8ebcb3e4106557461135faa1635e9b5370bd2d579fa6074979", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5004eefdda1dd24466fd6e9a86faa3d7fd10c95af54934b6e4aec83c12659db3", "generation_seconds_batch": 18.6349648530595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2483321875333786, "target_z": 0.05273438354825391, "ce": 5.839932441711426, "genuineness": 3.911123275756836, "identity": -0.040090128779411316, "hypothesis": "La puerta sigue abierta. He dejado tu abrijo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/2d68d9e17d65ae8ebcb3e4106557461135faa1635e9b5370bd2d579fa6074979.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": "2e276c5af2c3fbfbc21bcacdab8efeb2e72acd7537a6c63eb2dfaef24aadfe27", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fa4c73555cfcae9e563698e6b56394b73644edbab877f6bc2145c71f8a66954a", "generation_seconds_batch": 18.746871241019107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17076995968818665, "target_z": -0.10546873670271613, "ce": 6.070269584655762, "genuineness": 4.030367851257324, "identity": 0.6694296598434448, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd...", "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_Disgust/2e276c5af2c3fbfbc21bcacdab8efeb2e72acd7537a6c63eb2dfaef24aadfe27.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "2e5a6ade546e1fdb5892bd1eae122df9dde46c3c905de9bc417c279876716eb2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "34c899b487133566dbe4c6dd22a120670a4a3c4b1a8c96f382c4194292f93a3f", "generation_seconds_batch": 18.88002746796701, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02457195520401001, "target_z": -0.5039062405019401, "ce": 6.340320587158203, "genuineness": 4.18726921081543, "identity": 0.615651547908783, "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_Disgust/2e5a6ade546e1fdb5892bd1eae122df9dde46c3c905de9bc417c279876716eb2.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "2e9cc34ea13be6fddf86f1542269326884f4cabe4cf261f16518a84d030c19e3", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "af4398a5533e95962043e060598b91dd678538fa9a82d611c3cf21cfba352365", "generation_seconds_batch": 18.974820423987694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.018826603889465332, "target_z": -0.49218748860232814, "ce": 6.308549880981445, "genuineness": 3.835810661315918, "identity": 0.34949028491973877, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/2e9cc34ea13be6fddf86f1542269326884f4cabe4cf261f16518a84d030c19e3.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": "2ee2dd09783ce81adcf8c81854cdc322758531a5602a1b839f1b7e813d446f6c", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I wrote the number on the envelope.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eba7fbbc9ad387a53509a91e47ba19fd926a86a33b82bce03f28666242152efe", "generation_seconds_batch": 13.649958439986221, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27035602927207947, "target_z": 0.09765625569883594, "ce": 6.2767791748046875, "genuineness": 3.2584152221679688, "identity": 0.42026519775390625, "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_Disgust/2ee2dd09783ce81adcf8c81854cdc322758531a5602a1b839f1b7e813d446f6c.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": "2f003aa442748a8ca14e3cf1e54d97a0785c668ccb7ba3b14d5424ddce54cd98", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Escribí el número en el sobre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "866aa416e2cd18169a2d2b79ce516d9280034fb4d4fe34ba680214f2f19094c5", "generation_seconds_batch": 13.691169952973723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12193447351455688, "target_z": -0.20507812784941798, "ce": 5.990842819213867, "genuineness": 4.381826400756836, "identity": 0.6215952634811401, "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_Disgust/2f003aa442748a8ca14e3cf1e54d97a0785c668ccb7ba3b14d5424ddce54cd98.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": "2f1eaa9bea07fde333256b8eacf61d0f205c227350c214dc641b8d75016608b9", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Your message arrived after I had left.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "db2c6b0ef1a3a9253b3e41ec2f9115421f19cd67d3c8cafb5d93579afe7b3128", "generation_seconds_batch": 15.599344568094239, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16885483264923096, "target_z": -0.10937500759844793, "ce": 5.911416053771973, "genuineness": 3.7918784618377686, "identity": 0.24946512281894684, "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_Disgust/2f1eaa9bea07fde333256b8eacf61d0f205c227350c214dc641b8d75016608b9.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": "2f71c73338b19e7a23de1b2e1cc8b93778cc72087f173cc011b67a4587ba4f18", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a702df54108ddf53f181eede9f7e4ad339d78b3292f803cbef1ea3e189bcdef3", "generation_seconds_batch": 13.619347174069844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.402190089225769, "target_z": 2.406250075984479, "ce": 6.308549880981445, "genuineness": 4.068024158477783, "identity": 0.843852162361145, "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_Disgust/2f71c73338b19e7a23de1b2e1cc8b93778cc72087f173cc011b67a4587ba4f18.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "2fa33b84176cd3fa4cdb42d10177fc7eacd0dfa7ef9e916ed545180214a14797", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "17684a898862efa66cdb1927b6b437924d936c23ed3031b76d42fd3a2837e5e2", "generation_seconds_batch": 18.813863064046018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21577519178390503, "target_z": -0.013671887347477875, "ce": 6.221180438995361, "genuineness": 4.15588903427124, "identity": 0.7649071216583252, "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_Disgust/2fa33b84176cd3fa4cdb42d10177fc7eacd0dfa7ef9e916ed545180214a14797.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "2faa202df098a8754255fff722e1eebf5dce68a5654ee09a085c1801781cf75e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "11d57b1d0d295c6e0fe71722591b0a5f7c9903945759858cc49897b99ebd3e8a", "generation_seconds_batch": 22.760368408053182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1985391527414322, "target_z": -0.048828112652522127, "ce": 6.062326908111572, "genuineness": 4.149612903594971, "identity": 0.6111687421798706, "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_Disgust/2faa202df098a8754255fff722e1eebf5dce68a5654ee09a085c1801781cf75e.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "3036011fe95e2dfe8459cd95d9fb7be4a4def4ef113d7cc2105c619e1f1de4e8", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5bcfb23e07b1e8b28800a47351b56ed0172246e656809df620d4b715912869b2", "generation_seconds_batch": 21.140355481998995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013730376958847046, "target_z": -0.42578124810038803, "ce": 6.300607204437256, "genuineness": 4.482243061065674, "identity": 0.6073343753814697, "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_Disgust/3036011fe95e2dfe8459cd95d9fb7be4a4def4ef113d7cc2105c619e1f1de4e8.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "30c5a6563addebd4937e9786759c522cbd9319853df352f26d58461b5a4dbb6d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fd2ede5c3c44d5fdeee37d53fa896ed43a7598a20b925fbc2cfa59001955ee39", "generation_seconds_batch": 13.745130231021903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11235889047384262, "target_z": -0.22460937594980598, "ce": 5.8875885009765625, "genuineness": 3.9550557136535645, "identity": 0.6104278564453125, "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_Disgust/30c5a6563addebd4937e9786759c522cbd9319853df352f26d58461b5a4dbb6d.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "3127a375f8f4758429aa2cb2aa79ff0051a354aaecbb91fd340b84b84262e95a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ae8262ef6e15c808e2d236f4723711dab088bb5e3781818361e605ada5e9cee", "generation_seconds_batch": 21.655973118031397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21194496750831604, "target_z": -0.021484368351358068, "ce": 6.0305562019348145, "genuineness": 4.300237655639648, "identity": 0.610774576663971, "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_Disgust/3127a375f8f4758429aa2cb2aa79ff0051a354aaecbb91fd340b84b84262e95a.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": "318a147194dcfbf3a42bf4e7b71297bf73a7be80ddc6f8495e0582c21ab7523b", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Your message arrived after I had left.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8e2293a1e86a1c8c3e38560a1cfcfe4bb1029f6de08122cba6670115b1b31330", "generation_seconds_batch": 13.612508848891594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23971416056156158, "target_z": 0.035156255698835945, "ce": 6.046441555023193, "genuineness": 3.71028995513916, "identity": 0.3761727213859558, "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_Disgust/318a147194dcfbf3a42bf4e7b71297bf73a7be80ddc6f8495e0582c21ab7523b.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "318ed874e280cad8c90b3617b2127da930ce182688306baca03276641bdcf483", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3523a97f07145ff1ede9bd34b00cdbacd098353cce390adb0565d97c69707982", "generation_seconds_batch": 18.679843944031745, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2336598634719849, "target_z": 2.0625001823627502, "ce": 6.054384231567383, "genuineness": 3.9927117824554443, "identity": 0.4007244110107422, "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_Disgust/318ed874e280cad8c90b3617b2127da930ce182688306baca03276641bdcf483.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": "31cb3e3b4f8eb96db4ef19b97b5a44c5eead512261ec7ce8649b593b9bae739a", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "62e641977d2adf318074abd1ae2b8438a2aac8f7742d28f3d4c7ab1d1ce31353", "generation_seconds_batch": 13.644421658013016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38526302576065063, "target_z": 0.3320312329034922, "ce": 5.863759994506836, "genuineness": 4.231201171875, "identity": 0.5343347787857056, "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_Disgust/31cb3e3b4f8eb96db4ef19b97b5a44c5eead512261ec7ce8649b593b9bae739a.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "32f125a4878d8fbd2d36304ebf684f99b73115e7e05ec15124b43f27b9d714fc", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f576f5ac41c73092a8c5b7f487f67e3fad9d19e540aad468e5d5605507caecf6", "generation_seconds_batch": 19.44551635091193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.103091761469841, "target_z": -0.6640625265945678, "ce": 6.483288764953613, "genuineness": 4.080576419830322, "identity": 0.3761952221393585, "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_Disgust/32f125a4878d8fbd2d36304ebf684f99b73115e7e05ec15124b43f27b9d714fc.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "3312296bd76268f1d1859e9c93182779d8a7911fc839471abe05ed7037208d7d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c700d21690800d5daf754020cb620522f5c00e31cd46085189a4c8f29db37868", "generation_seconds_batch": 18.974820423987694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03414754569530487, "target_z": -0.5234375037992239, "ce": 6.348263263702393, "genuineness": 4.18726921081543, "identity": 0.4184725880622864, "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_Disgust/3312296bd76268f1d1859e9c93182779d8a7911fc839471abe05ed7037208d7d.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "33462daef423e07ac17e0c34d7eb8277ac15ca31cd349fe2c0ddaa53ab846fd6", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4188d55e8d4fa393e3bc2648aaafc72bd912c26d4f47a3adebceea96581fc375", "generation_seconds_batch": 20.67384302301798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1281585991382599, "target_z": -0.19238282342276888, "ce": 6.125868320465088, "genuineness": 4.507347106933594, "identity": 0.6948133111000061, "hypothesis": "Die Tür 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_Disgust/33462daef423e07ac17e0c34d7eb8277ac15ca31cd349fe2c0ddaa53ab846fd6.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "334c40ccc1cbfa36a68265b91269d94ded99e26fe10e433da628fb09857746c5", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "694ab911acec1726c49f7bbbf407545471f357ec7691eeb6d1fcd432e67aa48f", "generation_seconds_batch": 14.983021041029133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0015905648469924927, "target_z": -0.4570312632972839, "ce": 6.078212261199951, "genuineness": 4.532451152801514, "identity": 0.7743107080459595, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/334c40ccc1cbfa36a68265b91269d94ded99e26fe10e433da628fb09857746c5.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": "3391537325992f460e534d36c41ffa67558c095e19d4085658cd35db95ee7306", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Your message arrived after I had left.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9c7b64612bcaf87860c06172f097b9aef476905ce86ee8f1f655f519b720f7d7", "generation_seconds_batch": 15.599344568094239, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22630834579467773, "target_z": 0.007812511397671884, "ce": 6.292664527893066, "genuineness": 3.7918784618377686, "identity": 0.5477549433708191, "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_Disgust/3391537325992f460e534d36c41ffa67558c095e19d4085658cd35db95ee7306.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "4eae20492566d21a7acd612180b50ccad70d74547cc848340c2400fcd3dc9775", "generation_seconds_batch": 16.421365995076485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08075946569442749, "target_z": -0.28906249620077606, "ce": 6.109982967376709, "genuineness": 4.419482707977295, "identity": 0.7431647181510925, "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_Disgust/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "346afb89b3f6840025f5b0adad27dc608fa5c1f35423dbf702620537328e1ac1", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "21320f5ed7944673877f4264b6a06af40978c02ffb7588189bcfd40d013552fa", "generation_seconds_batch": 13.660672790952958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2949435710906982, "target_z": 2.187500121575167, "ce": 6.1020402908325195, "genuineness": 3.923675537109375, "identity": 0.6802558302879333, "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_Disgust/346afb89b3f6840025f5b0adad27dc608fa5c1f35423dbf702620537328e1ac1.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "e5c4cc7f5826a7d0d0f8fc55a2b22f4882b407db9d1d2a7f5a70c1713264dcf0", "generation_seconds_batch": 16.50649294501636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04437224566936493, "target_z": -0.36328124810038803, "ce": 6.292664527893066, "genuineness": 3.8420867919921875, "identity": 0.3984068036079407, "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_Disgust/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "34e06547699afc6b62b16a030deb13147f65475422c80422e68b1008c7b06802", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c8df014bf2c3b0bdefe5695a2c03ee2a6584849202a910bf2abc16b2332ea21c", "generation_seconds_batch": 22.249193405965343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7165782451629639, "target_z": 1.007812511397672, "ce": 6.181467056274414, "genuineness": 4.061748504638672, "identity": 0.830241858959198, "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_Disgust/34e06547699afc6b62b16a030deb13147f65475422c80422e68b1008c7b06802.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "34eafe50d4cb863da76637dc602a2bb2f88add70a97bec31d742a87e5711ada7", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7bd36b319cefbe42b83f81f5d2279f952cc0406651d10670bd7a796e7e174fae", "generation_seconds_batch": 21.76520595198963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4771886467933655, "target_z": 0.5195312632972838, "ce": 6.070269584655762, "genuineness": 4.18099308013916, "identity": 0.6113404035568237, "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_Disgust/34eafe50d4cb863da76637dc602a2bb2f88add70a97bec31d742a87e5711ada7.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "34ff3c680d8f257b4c461de44741c99b645375f678676ff88417d34e55a3c963", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4ff224784a895249e720bc918e773a50e9ca12a14fae514e42fa1fc565f44fc5", "generation_seconds_batch": 18.638018390047364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1966240257024765, "target_z": -0.05273438354825391, "ce": 6.308549880981445, "genuineness": 4.507347106933594, "identity": 0.5411356687545776, "hypothesis": "Die Tür 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_Disgust/34ff3c680d8f257b4c461de44741c99b645375f678676ff88417d34e55a3c963.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "351d662c44c49d466461797ead2ee6d943b8ab4bb7c0eb097674f3a9b40c23ab", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4812b13a5e0cb9993cc8b2313afba68a8d3d8c722685af6a6951b93a0d8a6a50", "generation_seconds_batch": 18.78640447196085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07692922651767731, "target_z": -0.2968750075984479, "ce": 6.038498878479004, "genuineness": 3.747946262359619, "identity": 0.2729966938495636, "hypothesis": "The 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_Disgust/351d662c44c49d466461797ead2ee6d943b8ab4bb7c0eb097674f3a9b40c23ab.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "35370b017beaa5fa483d48d7c8e65003df6bb31088d49632bbc4884f44a7c809", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "469a19bc3047c831234cf5146968aef44172ca11c9f312f8f866124bbb44e560", "generation_seconds_batch": 13.807074547978118, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07980190217494965, "target_z": -0.2910156316486419, "ce": 5.824047088623047, "genuineness": 3.9927117824554443, "identity": 0.6160476207733154, "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_Disgust/35370b017beaa5fa483d48d7c8e65003df6bb31088d49632bbc4884f44a7c809.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "3558396462ee759d6a5e2ea115f9f961abc51d76a7b5c6846be82075c0b73faa", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "34c4ada7f238b20dd275008172c5ff460c381033171c5abcf62d0a4d4a9b7a65", "generation_seconds_batch": 18.963250042055734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10709232091903687, "target_z": -0.23535156012548503, "ce": 6.109982967376709, "genuineness": 4.444586753845215, "identity": 0.5276134014129639, "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_Disgust/3558396462ee759d6a5e2ea115f9f961abc51d76a7b5c6846be82075c0b73faa.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "356129a3d1eda7ee25e34f935cc16e89270e7971a082ccfa44a88b66bb0d543d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a62ad8cb186a6bd5ac3ea0eb14eda556662d9ae019f900c9dcb713023973e02d", "generation_seconds_batch": 18.866027421085164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03096643090248108, "target_z": -0.3906249924015521, "ce": 5.927301406860352, "genuineness": 3.8295347690582275, "identity": 0.2804029583930969, "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_Disgust/356129a3d1eda7ee25e34f935cc16e89270e7971a082ccfa44a88b66bb0d543d.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "35875ab251bb724541b6f6de86b0d5a99ecfc0ea85dedf46a8c72ba3e1388de3", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d4cb8c2189e393a30ce1b36443c823be187b30d78c0953b175bf53ca45dff8bf", "generation_seconds_batch": 18.77192049100995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14204320311546326, "target_z": -0.16406249620077604, "ce": 6.229123115539551, "genuineness": 4.13078498840332, "identity": 0.5656459331512451, "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_Disgust/35875ab251bb724541b6f6de86b0d5a99ecfc0ea85dedf46a8c72ba3e1388de3.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": "35eacd47aeb10a777d75041dc712f441fe9d5c993177adacd286298e37fa8a1e", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "482ab385ca60080f9381d8d5c1a281701d55153dbeb7eabfcfb951f844ac7cbd", "generation_seconds_batch": 13.59272231592331, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3206278383731842, "target_z": 0.2001953044266491, "ce": 6.23706579208374, "genuineness": 3.7040140628814697, "identity": 0.4845186769962311, "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_Disgust/35eacd47aeb10a777d75041dc712f441fe9d5c993177adacd286298e37fa8a1e.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "3610b8956d857ba737816c1e25870d53d66604857623275946c55c0aa992386e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c95dcdbd389d28a823337bb3b70070b2412788ce00c8802b22e9a98b5eb8f8f2", "generation_seconds_batch": 15.088876342051663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08075946569442749, "target_z": -0.28906249620077606, "ce": 5.696964263916016, "genuineness": 4.2374773025512695, "identity": 0.7663044929504395, "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_Disgust/3610b8956d857ba737816c1e25870d53d66604857623275946c55c0aa992386e.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "3693e190ebaf2de0a9c06549c99df24074cc97a0523b8e762e18272e7b4812e3", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5497e5c58e62f854d5f6450b07e40cc5b1144f53d919142b0e6abb578d0feb2f", "generation_seconds_batch": 15.049607516033575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.005420789122581482, "target_z": -0.46484374430116404, "ce": 6.356205940246582, "genuineness": 4.519899368286133, "identity": 0.577643632888794, "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_Disgust/3693e190ebaf2de0a9c06549c99df24074cc97a0523b8e762e18272e7b4812e3.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "38195f314983f2de91ed84c0761509679011a4d2a6fc1bb53966ff311e1474a8", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b8babf5738e5ace0e0aad8c1193cee0569fe0f4f36497addfcee8c6cb4303f60", "generation_seconds_batch": 19.528966123005375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08075946569442749, "target_z": -0.28906249620077606, "ce": 6.165581703186035, "genuineness": 4.570107460021973, "identity": 0.6476855874061584, "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_Disgust/38195f314983f2de91ed84c0761509679011a4d2a6fc1bb53966ff311e1474a8.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "38887a078f4c93bb40fb691201ed8752c6871808afe93971d1c09f95265449db", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "21316bbe044c4bf9612ac58b80b01b0f37d53c3e7761d217d08c34642c4b7b66", "generation_seconds_batch": 14.72270370007027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24306561052799225, "target_z": 0.041992184175679036, "ce": 6.324435234069824, "genuineness": 4.419482707977295, "identity": 0.6342269778251648, "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_Disgust/38887a078f4c93bb40fb691201ed8752c6871808afe93971d1c09f95265449db.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "3b2789e0df5e70735ab581ba0dcfa51300910b0f6630b3069fc35440e1089feb", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f38056a153865afa0ac18955c0327b9d908dad541b4a7b98ee2b46ff9e91ff6f", "generation_seconds_batch": 14.139929078053683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.06095917522907257, "target_z": -0.5781249924015521, "ce": 6.332377910614014, "genuineness": 4.281409740447998, "identity": 0.43168556690216064, "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_Disgust/3b2789e0df5e70735ab581ba0dcfa51300910b0f6630b3069fc35440e1089feb.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "3bdd470467948fefd7801e2c06567162e18cc86121553c916ed3ca3c6efff4ea", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0353df33b9bffde86a33aae3223f4443cd17e8c9a2a0ae2f971ab63d8a67fa80", "generation_seconds_batch": 14.139929078053683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.08011035621166229, "target_z": -0.6171875189961198, "ce": 6.372091293334961, "genuineness": 4.482243061065674, "identity": 0.5405344367027283, "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_Disgust/3bdd470467948fefd7801e2c06567162e18cc86121553c916ed3ca3c6efff4ea.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "3be820791a522ad113b3c641aa282ed25744683472d4e2b9be69ab1f6192c6cf", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "07fe8351b778614c74035a619a73868d5b2de8094cca3e7c801e310d6e6ba849", "generation_seconds_batch": 18.630437768995762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07501411437988281, "target_z": -0.30078124810038803, "ce": 6.125868320465088, "genuineness": 4.432034492492676, "identity": 0.564457356929779, "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_Disgust/3be820791a522ad113b3c641aa282ed25744683472d4e2b9be69ab1f6192c6cf.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "3becf1ce79982ee59f0eb0b2c5489abeba5c97112daa2e76342b9c75a7e3c0dd", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "21f1271cdb696335cd1023545f5de7fddbc0219373b93071b4ad258ed6b370a9", "generation_seconds_batch": 20.00499614002183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010857701301574707, "target_z": -0.431640624050194, "ce": 6.149696350097656, "genuineness": 4.457139015197754, "identity": 0.8211522698402405, "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_Disgust/3becf1ce79982ee59f0eb0b2c5489abeba5c97112daa2e76342b9c75a7e3c0dd.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "3c403015a1318d6e9a5b8c9e20e68a2be56cecdb9dcbb4cf6ae12b1eb75090f4", "bucket": "emo_Disgust", "phase": "wording", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8e5e1d1ba6a4f002ae0764ea4342fef1997a674a80cb6cb01c5d5b1c0c234a92", "generation_seconds_batch": 14.042485764017329, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1535339057445526, "target_z": -0.14062499240155207, "ce": 6.197352409362793, "genuineness": 4.18099308013916, "identity": 0.5901162624359131, "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_Disgust/3c403015a1318d6e9a5b8c9e20e68a2be56cecdb9dcbb4cf6ae12b1eb75090f4.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "3c41ec9a7223286a2cdb0accd0945d8d1982f639ae170ddcf7358706e020e8e9", "bucket": "emo_Disgust", "phase": "wording", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5626af4190ebbb6ac52e0b77aeaad38a23adc51f92ff1959baa3e5799d65537c", "generation_seconds_batch": 16.536070364993066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.026487082242965698, "target_z": -0.5078125113976719, "ce": 6.38797664642334, "genuineness": 4.306513786315918, "identity": 0.6542630195617676, "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_Disgust/3c41ec9a7223286a2cdb0accd0945d8d1982f639ae170ddcf7358706e020e8e9.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "e57d95a336f6fc6aafe0262a380aaedb77b12e7b6f1722fcbe8a66e60f409c61", "generation_seconds_batch": 13.811165546067059, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032881543040275574, "target_z": -0.38671875189961197, "ce": 6.181467056274414, "genuineness": 4.432034492492676, "identity": 0.7041659355163574, "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_Disgust/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "3c5abf736bd3aebd3e5f4b0dce89369f175e6eb50289a5cd1051dc768ef141c7", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6e961cb99028ad59048ea477624abdcf7f0834c82c542953a9a3e911e9add214", "generation_seconds_batch": 18.585920298937708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16119436919689178, "target_z": -0.125, "ce": 5.796247482299805, "genuineness": 3.6663577556610107, "identity": 0.6815332770347595, "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_Disgust/3c5abf736bd3aebd3e5f4b0dce89369f175e6eb50289a5cd1051dc768ef141c7.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": "3c8ced5e78f3b141c41a8e3130c838d7e1fef8dbccdd9d5486242138d818c97a", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c9cc5a5974a9eb3097b5851cd2d4600e6cfaa66d1cb37541b1c50dec70d8e29d", "generation_seconds_batch": 13.74069068301469, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33355486392974854, "target_z": 0.22656246580698436, "ce": 6.213237762451172, "genuineness": 3.8671910762786865, "identity": 0.5192023515701294, "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_Disgust/3c8ced5e78f3b141c41a8e3130c838d7e1fef8dbccdd9d5486242138d818c97a.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "3c8d8b3d0d477fb144c17a2609a0f8c2fa071e7780d944b55bd8a1324ccf9e65", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b4026b2601b5ea58cb980653945af75549ae49d2ceec77715d19ca879e4ee34e", "generation_seconds_batch": 19.1083247900242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.06095917522907257, "target_z": -0.5781249924015521, "ce": 6.3641486167907715, "genuineness": 3.9927117824554443, "identity": 0.4294937551021576, "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_Disgust/3c8d8b3d0d477fb144c17a2609a0f8c2fa071e7780d944b55bd8a1324ccf9e65.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "3cb52d823f7b73e23e4dfd8d4b6f66a915dfa2501e46243150e0d6f6ee6f9ec8", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "601898735711a1682d09b2782b242991e9663d2d080b0b4c727c517e8c4ed765", "generation_seconds_batch": 22.647154180915095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08363214135169983, "target_z": -0.28320312025097005, "ce": 6.165581703186035, "genuineness": 4.231201171875, "identity": 0.6590098738670349, "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_Disgust/3cb52d823f7b73e23e4dfd8d4b6f66a915dfa2501e46243150e0d6f6ee6f9ec8.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "3ce88a11f8d03489ea8b2659e561341315066e15f068059edc8e398530b2351b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2c5d3f9f68cad45cba1f10790cf5062104ff235b36c54038abec88a78463727d", "generation_seconds_batch": 18.680003194953315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11427401006221771, "target_z": -0.22070312025097005, "ce": 5.935244083404541, "genuineness": 3.6663577556610107, "identity": 0.15708860754966736, "hypothesis": "The 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_Disgust/3ce88a11f8d03489ea8b2659e561341315066e15f068059edc8e398530b2351b.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "3d983a9fc236651576bc0e31bd479b17736ca0ba4a685c449dc194d5b2b753ac", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3cc85e3e5b2ee215b4bbbd1bf9482c4b058e21b327b04ceee25cf02c5af2cd2b", "generation_seconds_batch": 16.098389495979063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07788679003715515, "target_z": -0.294921872150582, "ce": 6.252951145172119, "genuineness": 3.8044304847717285, "identity": 0.41973018646240234, "hypothesis": "The 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_Disgust/3d983a9fc236651576bc0e31bd479b17736ca0ba4a685c449dc194d5b2b753ac.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "3ddd227d3d8b38a891ae35c630233c9f7c66aa1680886161f771c3dce831f540", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8900387bd433fe9997a05c37eea34739248e71c0c9313f37c2023d11112c66c3", "generation_seconds_batch": 15.254098939010873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20619961619377136, "target_z": -0.033203120250970046, "ce": 6.221180438995361, "genuineness": 4.20609712600708, "identity": 0.3231268525123596, "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_Disgust/3ddd227d3d8b38a891ae35c630233c9f7c66aa1680886161f771c3dce831f540.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "3e8116cde461f60287a834790bea180cc1a923fcc94174b970b296ad160d4cf0", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d18f8e23a3499f4ab2ff7830901cc5d5d58c374e3f18ee01fc34d340158d0492", "generation_seconds_batch": 19.837828695075586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0820254534482956, "target_z": -0.6210937291042682, "ce": 6.372091293334961, "genuineness": 4.369274139404297, "identity": 0.3429792821407318, "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_Disgust/3e8116cde461f60287a834790bea180cc1a923fcc94174b970b296ad160d4cf0.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "3f586033e7f7c3f827cec3a15c2200fa10d8706c7a1fc65516eb7684135b37ff", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f5a6d2c66c073297aa46946c3ac4e91f06088181f2d1c6a1e7a517210ec92a06", "generation_seconds_batch": 21.057148964959197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.005420789122581482, "target_z": -0.46484374430116404, "ce": 6.348263263702393, "genuineness": 4.256305694580078, "identity": 0.6379010081291199, "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_Disgust/3f586033e7f7c3f827cec3a15c2200fa10d8706c7a1fc65516eb7684135b37ff.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": "3f7b4299d5589ce6950ea743b1a90899cc727c61d9183aea075f880feb1f72e6", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Escribí el número en el sobre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d3b3689860cf93e5b7e5ac3d0fe139dfd859e4813bc8eb681d83c332e44e7b9f", "generation_seconds_batch": 18.529036583960988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12097691744565964, "target_z": -0.20703124810038803, "ce": 6.078212261199951, "genuineness": 4.111956596374512, "identity": 0.6600790619850159, "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_Disgust/3f7b4299d5589ce6950ea743b1a90899cc727c61d9183aea075f880feb1f72e6.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "3f96198b947293de982dcf474c31cfce4c72658477a52d75f584587c80171c3f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "673c238daa19227b2586663923db4243420ef48a7cef55aae94bfcac5f7e6b68", "generation_seconds_batch": 19.004906325018965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05904404819011688, "target_z": -0.5742187215058203, "ce": 6.1020402908325195, "genuineness": 4.413206577301025, "identity": 0.677019476890564, "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_Disgust/3f96198b947293de982dcf474c31cfce4c72658477a52d75f584587c80171c3f.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "3fcf0ab37fc26c1f22bbfb94df1ba9ac55aece83514af308e1b91d2853f3c7f2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c9ee4099af4fcc71b33b0f1def217974fb6d6d503328e2a0579ad47b8a0c19bd", "generation_seconds_batch": 21.09830873494502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06256584823131561, "target_z": -0.3261718873474779, "ce": 6.300607204437256, "genuineness": 4.268857479095459, "identity": 0.440439909696579, "hypothesis": "Die Tür 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_Disgust/3fcf0ab37fc26c1f22bbfb94df1ba9ac55aece83514af308e1b91d2853f3c7f2.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "3fdf9ca2dd0bc7e7df89bc88eb9a202f8db5aa90273df5bacc40ff68babdc300", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "e62393e92ff7fde0bfcd9d06460c49390b7213bd95ec222b54f131c401dfd4e3", "generation_seconds_batch": 18.999710357980803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.022656843066215515, "target_z": -0.5, "ce": 6.125868320465088, "genuineness": 4.494794845581055, "identity": 0.6103115081787109, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/3fdf9ca2dd0bc7e7df89bc88eb9a202f8db5aa90273df5bacc40ff68babdc300.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "3fe88f272865fc1822a8bcc9b016d38279827b58a95005399ca820fb52ae50bc", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5665dfac1e75e7d18682e600b8181c3fb5d5450e025294aa47f1ea89ef22ceaf", "generation_seconds_batch": 22.67110387806315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021390840411186218, "target_z": -0.41015625569883596, "ce": 5.919358730316162, "genuineness": 4.268857479095459, "identity": 0.652126133441925, "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_Disgust/3fe88f272865fc1822a8bcc9b016d38279827b58a95005399ca820fb52ae50bc.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "400d043590abe31aad39ac372c6208aa2374400221ccb8c3897135215dc69b41", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "42ba5cc0718128fd60065e840bd190ed3fcad3d13b3c26ef0e5de66ea58429d8", "generation_seconds_batch": 20.48421991802752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.030348300933838, "target_z": 3.687499878424833, "ce": 6.165581703186035, "genuineness": 3.575355052947998, "identity": 0.5072400569915771, "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_Disgust/400d043590abe31aad39ac372c6208aa2374400221ccb8c3897135215dc69b41.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "40336375a9b2b43c1e0705d5d5efc1d8017e48f2adb82902e6b22da21d59d1ce", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9345109c51fca7d3f93eb7fbed725758cb97983f50c73fa503aab4e742a04c2b", "generation_seconds_batch": 18.828468912979588, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10182575136423111, "target_z": -0.24609374430116407, "ce": 6.125868320465088, "genuineness": 4.256305694580078, "identity": 0.6523574590682983, "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_Disgust/40336375a9b2b43c1e0705d5d5efc1d8017e48f2adb82902e6b22da21d59d1ce.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "40404fa5647c91675817cd80f189f9af0b38f36b3dd55e10283ebdf4536f0375", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "133678f72ec8f8f7299a03e1fd432c22b984cfe4e2f541d798c0b43beab7c74d", "generation_seconds_batch": 13.776923118974082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.07244987785816193, "target_z": -0.6015624962007761, "ce": 6.41180419921875, "genuineness": 4.381826400756836, "identity": 0.2757669687271118, "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_Disgust/40404fa5647c91675817cd80f189f9af0b38f36b3dd55e10283ebdf4536f0375.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "404999dac50c03c9fb3e99bbca756c0233f0974e18c09e1bf172cc78d89c223d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f8060b72f5d25eb46abbb4be49430d267ea5a4f6d170a99a68b5499ee5bd0237", "generation_seconds_batch": 22.7997506079264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009900137782096863, "target_z": -0.4335937594980599, "ce": 6.23706579208374, "genuineness": 4.570107460021973, "identity": 0.689862847328186, "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_Disgust/404999dac50c03c9fb3e99bbca756c0233f0974e18c09e1bf172cc78d89c223d.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "4056f2cf57f44ee2f8ed5382a68885501a1226680db0da51c1c97b8fa38b224a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e2c3465bb98f6685a0a3ea894cba15faac0c1ec84e6f1875d7c1fe88b09e2da0", "generation_seconds_batch": 19.59495813504327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09225016832351685, "target_z": -0.2656249924015521, "ce": 6.149696350097656, "genuineness": 3.6412534713745117, "identity": 0.4708574712276459, "hypothesis": "The 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_Disgust/4056f2cf57f44ee2f8ed5382a68885501a1226680db0da51c1c97b8fa38b224a.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "40920a335ff37c68b93a32e8c36f3795f197e73ccd606e2ca5de296515cec2b1", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ce3fe17f9bb0f9030f17cec9b7a5d3278674c67807609b0e39c8c27976bfdff", "generation_seconds_batch": 19.459954573074356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12097691744565964, "target_z": -0.20703124810038803, "ce": 5.9431867599487305, "genuineness": 4.256305694580078, "identity": 0.6900664567947388, "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_Disgust/40920a335ff37c68b93a32e8c36f3795f197e73ccd606e2ca5de296515cec2b1.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "4095b811af0a276ca982af9646b213a101c94a825058467ac8ecaf139d1533f8", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "09a22db3eb916e03387eeef66d1367e2a1f6650d5940bd4d33f2fb3a5500ae04", "generation_seconds_batch": 13.88762010994833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16310948133468628, "target_z": -0.12109375949805991, "ce": 6.308549880981445, "genuineness": 3.8169827461242676, "identity": 0.5962411165237427, "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_Disgust/4095b811af0a276ca982af9646b213a101c94a825058467ac8ecaf139d1533f8.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": "41416e1ebfddefc3ff4ca7bc25fe8ec6eac00e77ca5a5f3f1dae9fbb47d7c541", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ee3e3c80f47c790e232b7d2d4067d23e8442e414915801c2d341b13c2680a078", "generation_seconds_batch": 18.49379915499594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1146135330200195, "target_z": 3.8593750683860315, "ce": 6.24500846862793, "genuineness": 3.6663577556610107, "identity": 0.39503031969070435, "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_Disgust/41416e1ebfddefc3ff4ca7bc25fe8ec6eac00e77ca5a5f3f1dae9fbb47d7c541.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "41709080b1b31c863a3472a05d4ef380c3f384a19186b6d44606813bbc04960b", "bucket": "emo_Disgust", "phase": "wording", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b6e026d1c514037a128bf3088220e37547e28715ec67ddcf566da456b3850c7f", "generation_seconds_batch": 17.709500534110703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1056559830904007, "target_z": -0.23828124810038803, "ce": 6.356205940246582, "genuineness": 4.545003414154053, "identity": 0.5375499725341797, "hypothesis": "Die Tür 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_Disgust/41709080b1b31c863a3472a05d4ef380c3f384a19186b6d44606813bbc04960b.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "42705dfa9b335fa9cc026729c92236167ef4beeea7318ac9b5cba93b5c58481f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "986ae394adca595e1733f044f9d6bafe60d0377a67fea02a2e622e07a524fc3a", "generation_seconds_batch": 18.859513973002322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08650481700897217, "target_z": -0.27734374430116404, "ce": 6.332377910614014, "genuineness": 4.218649387359619, "identity": 0.4975552558898926, "hypothesis": "The 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_Disgust/42705dfa9b335fa9cc026729c92236167ef4beeea7318ac9b5cba93b5c58481f.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "428baa69b76b5e07854729a5681e8280af2675942463649c135d26369095e932", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4e68b6bf494a76e908c8b38102bfe3a344f27a6fc61345e0f328426bee7b5289", "generation_seconds_batch": 18.783591369981878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07501411437988281, "target_z": -0.30078124810038803, "ce": 6.23706579208374, "genuineness": 4.7081804275512695, "identity": 0.609281599521637, "hypothesis": "Die Tür 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_Disgust/428baa69b76b5e07854729a5681e8280af2675942463649c135d26369095e932.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "431b26433eccd66d40ed2ed1bb9621a41ec73c56752eb386145aa0f8499f0e02", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "380848ef3dd2a76a86b518ac495f4805494851abaf52258a6cae31262d1a141f", "generation_seconds_batch": 18.57110298308544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7315901517868042, "target_z": 3.078125022795344, "ce": 6.165581703186035, "genuineness": 3.7291181087493896, "identity": 0.4071144163608551, "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_Disgust/431b26433eccd66d40ed2ed1bb9621a41ec73c56752eb386145aa0f8499f0e02.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "0a27f171933783246ac505ada6ed1ade7cf21d56f6d7b13e0134c394de733646", "generation_seconds_batch": 16.421365995076485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09799551218748093, "target_z": -0.25390625569883596, "ce": 6.109982967376709, "genuineness": 4.469690799713135, "identity": 0.6165273785591125, "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_Disgust/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.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": "436e3ed3d5d2c5f3f78ef90ea877c46618807ed08885c782227414443b05e051", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7e72dd193ca91a308255cdcb06cca0e5a0259a796ac018b29735372ae9ff8400", "generation_seconds_batch": 13.714193867053837, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21673275530338287, "target_z": -0.01171875189961198, "ce": 6.483288764953613, "genuineness": 4.243753433227539, "identity": 0.49137982726097107, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier, naast de hoge boekenkast. We zetten het naar de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/436e3ed3d5d2c5f3f78ef90ea877c46618807ed08885c782227414443b05e051.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "43d1ea08b728db85f8890fd9cd08e4d0924f917ed52f55881e190069df5b5af8", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4f9a9e388e0110881853840736f27a550bd0eb4484890969f6ac95310235e171", "generation_seconds_batch": 19.421046264935285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1324676275253296, "target_z": -0.18359372910426822, "ce": 6.070269584655762, "genuineness": 4.193545341491699, "identity": 0.6054795980453491, "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_Disgust/43d1ea08b728db85f8890fd9cd08e4d0924f917ed52f55881e190069df5b5af8.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8bacb25a202d09dc0450647a15c13e343194f99dea0371fc26cd9e4bf230d1c9", "generation_seconds_batch": 13.678953233058564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.053947821259498596, "target_z": -0.34375001519689585, "ce": 6.284721851348877, "genuineness": 4.507347106933594, "identity": 0.6353746652603149, "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_Disgust/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "43f98f9f4216260392decdfe723bb7ff935f95d68d91aec41da05d07e3df645a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "26278107290e35976dda4394024d02b1102eb8f00ebcc31ed722681e9cf38503", "generation_seconds_batch": 18.858347604982555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.016911491751670837, "target_z": -0.48828124810038803, "ce": 6.419747352600098, "genuineness": 4.293961524963379, "identity": 0.5901912450790405, "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_Disgust/43f98f9f4216260392decdfe723bb7ff935f95d68d91aec41da05d07e3df645a.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "44350c821eb2f4a91a5fd9e7a19ed755b2b87d253c89e2673f24035e3083dcf5", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5639a4a74228001cb3d46603a5a5333b532d7ad49999e8ae89648b3ad17c8b01", "generation_seconds_batch": 19.188951906980947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08554725348949432, "target_z": -0.27929687974902995, "ce": 6.165581703186035, "genuineness": 4.2374773025512695, "identity": 0.5550692677497864, "hypothesis": "Ik heb het kleine doosje gevonden. Stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/44350c821eb2f4a91a5fd9e7a19ed755b2b87d253c89e2673f24035e3083dcf5.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "445f44fd5ee7ec3cf7624e7b542dbdd7a74e00c5bb3f05d5c4a6aa4a7009f586", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "6850a50c8a78c48c6e3aef65c2fc1919638f946051bcca8b8e58a8029dd31b17", "generation_seconds_batch": 19.834188638953492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011815264821052551, "target_z": -0.42968748860232814, "ce": 6.284721851348877, "genuineness": 4.281409740447998, "identity": 0.4785881042480469, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/445f44fd5ee7ec3cf7624e7b542dbdd7a74e00c5bb3f05d5c4a6aa4a7009f586.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "447545bc423169323f7d936515628f59ba42f2ee1462c1c76adf354d639afcfa", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "43ca70cc0dcc61f6b4278831d7dcab416effdfe2d7cfd3547989aaf3ee54e15c", "generation_seconds_batch": 18.60438604198862, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07118387520313263, "target_z": -0.3085937594980599, "ce": 6.038498878479004, "genuineness": 4.024092197418213, "identity": 0.7345061898231506, "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_Disgust/447545bc423169323f7d936515628f59ba42f2ee1462c1c76adf354d639afcfa.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "44cfafdd4fb61b2e9433971cb3a3359a042afc643dc3edb8f64a9eee6a9bf6ab", "bucket": "emo_Disgust", "phase": "wording", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ff0a9bc18709f75ac73f5bdfb842f1a55465bbe35c6b09e0c7385d722108a3fc", "generation_seconds_batch": 14.122584111988544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07501411437988281, "target_z": -0.30078124810038803, "ce": 6.141753673553467, "genuineness": 4.281409740447998, "identity": 0.6376393437385559, "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_Disgust/44cfafdd4fb61b2e9433971cb3a3359a042afc643dc3edb8f64a9eee6a9bf6ab.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": "4538ccf0b0cb73c5e206334337f801148254fdaeb6d9aef51d520f83afca4ee4", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d93ea39e8f5c3c79340ad424a770b42426814e091f67a7c7e483760eef123e52", "generation_seconds_batch": 14.030819098930806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12384959310293198, "target_z": -0.20117187215058202, "ce": 5.974957466125488, "genuineness": 3.998987913131714, "identity": 0.5844534635543823, "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_Disgust/4538ccf0b0cb73c5e206334337f801148254fdaeb6d9aef51d520f83afca4ee4.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "4573d14123d5990e5bca6e7929888b493d36bad7668397ea73301b8a1422c9ce", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "43939e2f93c299230d3eea1e3694aaedebb23fcca1f8dae0bfa1b986e529f759", "generation_seconds_batch": 18.933402633061633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08075946569442749, "target_z": -0.28906249620077606, "ce": 6.292664527893066, "genuineness": 4.557555198669434, "identity": 0.6396859884262085, "hypothesis": "Die Tür 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_Disgust/4573d14123d5990e5bca6e7929888b493d36bad7668397ea73301b8a1422c9ce.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": "45d3ed736430f2bdb40147ccf2f0fc17099ba708c9246b36d336fbb15136c511", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "81cf06a42538677f3dbc07a08f0d5a9648c43122fb4d077ce30d24d10390542e", "generation_seconds_batch": 13.653173040947877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03192397952079773, "target_z": -0.3886718873474779, "ce": 5.982900142669678, "genuineness": 4.21237325668335, "identity": 0.6644641757011414, "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_Disgust/45d3ed736430f2bdb40147ccf2f0fc17099ba708c9246b36d336fbb15136c511.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": "45e30b549c0103d1131edbe5c317b24fe3c65216cb04321a915162e1410c3540", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a4fe5d11f76378b1f8b2ecf44cc0a4d5b86c8b91f402dfe7301e15c78a93dd3e", "generation_seconds_batch": 18.638177991029806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7162692546844482, "target_z": 3.046875098779823, "ce": 5.808161735534668, "genuineness": 3.503180742263794, "identity": 0.33975017070770264, "hypothesis": "La route tourne, gauche après le boum, continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.1, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/45e30b549c0103d1131edbe5c317b24fe3c65216cb04321a915162e1410c3540.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "45e4237daed70b3239969dfc93d4a44e9c2d617188b39a30aa332c4f3caa799c", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "10d0430f8d71ccc5d2c0e18ffb2ce1dd43ff38ea117befe7333814660c08dad5", "generation_seconds_batch": 18.660559147945605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03479665517807007, "target_z": -0.38281251139767186, "ce": 6.165581703186035, "genuineness": 4.1998209953308105, "identity": 0.6692714691162109, "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_Disgust/45e4237daed70b3239969dfc93d4a44e9c2d617188b39a30aa332c4f3caa799c.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "124c06dd906c3a50f0a20547dd3ec58790e6c77d91275e05a0c79bd526bb2b75", "generation_seconds_batch": 14.181236278964207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.052990272641181946, "target_z": -0.34570312025097005, "ce": 6.340320587158203, "genuineness": 4.2374773025512695, "identity": 0.6264652013778687, "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_Disgust/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "4651804924ccc1965ab64e27bd1d30ffc9ede6f2cae57c13906e9c05db73d2b5", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4ca50eb4fa0b4d42ba9efbd1c9a2fdd5b1a96f98d3bb7fbde59acd320ff49fc4", "generation_seconds_batch": 19.52521394798532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.321446180343628, "target_z": 4.281250136772063, "ce": 6.165581703186035, "genuineness": 3.7542223930358887, "identity": 0.5763270854949951, "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_Disgust/4651804924ccc1965ab64e27bd1d30ffc9ede6f2cae57c13906e9c05db73d2b5.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "471d03484ea21c20c835c2420d96ea13a6b318be96bc317205cbd7d477b237b2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "077ef6b2aa32d87a0703f7b174870e9be19be5b15e1f9bcc6c079ed5fbb0bf3a", "generation_seconds_batch": 13.776923118974082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.06861965358257294, "target_z": -0.5937500151968959, "ce": 6.356205940246582, "genuineness": 4.432034492492676, "identity": 0.37343913316726685, "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_Disgust/471d03484ea21c20c835c2420d96ea13a6b318be96bc317205cbd7d477b237b2.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "4748f6952ac4f9766b0d8c3c119ebbb877396e4b374e1bb9341c5609d18a8031", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c0f01fa360e65ee8187ceebd720440eb39d73df5babf287d1dc4aa32187e09b2", "generation_seconds_batch": 18.742161770001985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05521382391452789, "target_z": -0.5664062405019401, "ce": 6.475345611572266, "genuineness": 4.645420074462891, "identity": 0.3588217496871948, "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_Disgust/4748f6952ac4f9766b0d8c3c119ebbb877396e4b374e1bb9341c5609d18a8031.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "4751230330ce647d02133f80b2643aa5d401715918a3dc1d7ad588682dec4663", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0b5039cc38acf1ab55e9648c202fb5f9d4dd35fa28813f8dc940dc52bb01034c", "generation_seconds_batch": 20.595729092950933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03383910655975342, "target_z": -0.38476561645174606, "ce": 6.229123115539551, "genuineness": 4.243753433227539, "identity": 0.42214393615722656, "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_Disgust/4751230330ce647d02133f80b2643aa5d401715918a3dc1d7ad588682dec4663.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "479cdf19c2b596e1e74f345a67dd97e8e19fc56bad31468d820f93f8d2a028c5", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bdd8bd04d8689cab752ec7a15658e9b8d7e76d2094794c8613d066d5cd98e371", "generation_seconds_batch": 18.58229629904963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2030179500579834, "target_z": 2.000000091181375, "ce": 5.585766792297363, "genuineness": 3.553389072418213, "identity": 0.34665632247924805, "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_Disgust/479cdf19c2b596e1e74f345a67dd97e8e19fc56bad31468d820f93f8d2a028c5.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "47a5454ede80f4135c93608ae9327335b8e5b67471f67445167e4d49265c4e53", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ef092b9d2e002e0afa07643411d6456b446ac54f0b2f4d5b9b9f3dfd57c90963", "generation_seconds_batch": 19.227150340098888, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12959495186805725, "target_z": -0.1894531050540742, "ce": 5.967014789581299, "genuineness": 4.049196243286133, "identity": 0.5933853387832642, "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_Disgust/47a5454ede80f4135c93608ae9327335b8e5b67471f67445167e4d49265c4e53.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "02b173f71be5c3cd6ef95bb642cfd2fcdc032c7becc7f0977c1214b59ea77c11", "generation_seconds_batch": 13.635752356029116, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055862948298454285, "target_z": -0.33984374430116404, "ce": 6.213237762451172, "genuineness": 4.557555198669434, "identity": 0.7062405347824097, "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_Disgust/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "483a711ca27c6271dc8d9df5de3d4bde42306d17b365114df1aaa959f9d99a50", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b9281888b099a3df076f355d5cfacfb5e25de3e97270094801808b8802520cd5", "generation_seconds_batch": 20.543687414028682, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04724492132663727, "target_z": -0.357421872150582, "ce": 6.141753673553467, "genuineness": 3.9801597595214844, "identity": 0.25427520275115967, "hypothesis": "The 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_Disgust/483a711ca27c6271dc8d9df5de3d4bde42306d17b365114df1aaa959f9d99a50.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "48c474cf2c5794093b0df5b90f504ece913e460a1ad231b3c4c1de57fd874b0e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "224fbd55fd3e03e547887804fe68696f156ffaf3fcf2769416c7dd3b7743fdee", "generation_seconds_batch": 18.742161770001985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0820254534482956, "target_z": -0.6210937291042682, "ce": 6.467403411865234, "genuineness": 4.469690799713135, "identity": 0.3165334463119507, "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_Disgust/48c474cf2c5794093b0df5b90f504ece913e460a1ad231b3c4c1de57fd874b0e.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "493a32e506205ab1049178c76da6532ceeafed5fe702bc0ce5734cdc8c5dd0fe", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a0bb38202000a5205244b93e1d3cd46ea081f7e62c00b03fe9712d75944f3877", "generation_seconds_batch": 20.262878926936537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027136191725730896, "target_z": -0.39843750379922394, "ce": 6.403861999511719, "genuineness": 4.268857479095459, "identity": 0.30585038661956787, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie standen neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/493a32e506205ab1049178c76da6532ceeafed5fe702bc0ce5734cdc8c5dd0fe.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "494578c866c667bf125495e431b3ca292f1d5c55a57ba0668a2493b9e6b8e1a4", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b3cc5f90d9b9ade45bfef2c17b4c82923e0766c3aa4a87650e45d41ab213f2fe", "generation_seconds_batch": 19.251254974049516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021390840411186218, "target_z": -0.41015625569883596, "ce": 6.308549880981445, "genuineness": 4.758388519287109, "identity": 0.5282645225524902, "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_Disgust/494578c866c667bf125495e431b3ca292f1d5c55a57ba0668a2493b9e6b8e1a4.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "49613ca91d2e23efed36814978592fafcee3eef650a7bd5d11c312d651888057", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ae55af30b077353aba75086ef158634bdadfa0aeb09c63554f09cd46f16d8b48", "generation_seconds_batch": 15.049607516033575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.005420789122581482, "target_z": -0.46484374430116404, "ce": 6.117925643920898, "genuineness": 4.457139015197754, "identity": 0.6191858053207397, "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_Disgust/49613ca91d2e23efed36814978592fafcee3eef650a7bd5d11c312d651888057.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "f5dc9a6a8b7edc645cafa4ec2f1336659bd7542dcd30389c7bd58cf8f7f78938", "generation_seconds_batch": 13.69885648903437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.046287357807159424, "target_z": -0.3593750075984479, "ce": 6.213237762451172, "genuineness": 4.419482707977295, "identity": 0.6179602146148682, "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_Disgust/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "4a27d4293a21e746bb5ba48b72e970769db57dd8b9bb4bf00d57afc001e114ab", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7b096ec90da7c6c84af07d401b4e8556362daeb7889c6fa4b11a9e7d73c4249f", "generation_seconds_batch": 18.88820292800665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06926876306533813, "target_z": -0.3125, "ce": 6.109982967376709, "genuineness": 4.3504462242126465, "identity": 0.6413474678993225, "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_Disgust/4a27d4293a21e746bb5ba48b72e970769db57dd8b9bb4bf00d57afc001e114ab.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "4a8e9e1a0a28891594ab47546b7ef0632f622f96571ba7f4440f4b048ab88822", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "530bd687c70ac0ba918bae90caaaef946fb0e7906f36defc91e89e7732fa0392", "generation_seconds_batch": 13.75426655204501, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7280689477920532, "target_z": 1.0312500151968957, "ce": 4.574069023132324, "genuineness": 3.415316104888916, "identity": 0.3607653081417084, "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_Disgust/4a8e9e1a0a28891594ab47546b7ef0632f622f96571ba7f4440f4b048ab88822.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "4b0544fe18f39296fb2fbaa54140e2032f1d17271a1f695adc9f1ed45d2face5", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "18ee00015326f789326bbd4bf89a79286c9df7dfd575008a76ef419d050ad99f", "generation_seconds_batch": 18.9378470829688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1535339057445526, "target_z": -0.14062499240155207, "ce": 5.982900142669678, "genuineness": 4.011539936065674, "identity": 0.6004854440689087, "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_Disgust/4b0544fe18f39296fb2fbaa54140e2032f1d17271a1f695adc9f1ed45d2face5.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "4b4a435c8743316518a5d8a144cbcf37369e45dc6cf89605608f642b9915e68a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d3613236145f37419d4a1ce647557e5d9282d6c7ef8e330a419bbd9be199e43e", "generation_seconds_batch": 20.275206129066646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.08011035621166229, "target_z": -0.6171875189961198, "ce": 6.459460258483887, "genuineness": 4.325342178344727, "identity": 0.3994305729866028, "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_Disgust/4b4a435c8743316518a5d8a144cbcf37369e45dc6cf89605608f642b9915e68a.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "4b7308756efcc9e9fc564a30382ee94fed87fb98c6173d61a8a972e07c8ebb54", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ac2530b1b707f704bd68a6de04654cc60f5b9c0e7b543c9e6e9c6a82da89a38c", "generation_seconds_batch": 18.962900861050002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03575421869754791, "target_z": -0.380859375949806, "ce": 6.284721851348877, "genuineness": 4.482243061065674, "identity": 0.8371267318725586, "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_Disgust/4b7308756efcc9e9fc564a30382ee94fed87fb98c6173d61a8a972e07c8ebb54.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "4beec27579fb6d6e2f3490befcbdd476f289a86695bc8fcd794c58911043619e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "57e6810c32f47fc347cd95c71d4a405bff5cad3d4394fe68330f6061aca05454", "generation_seconds_batch": 15.798123402055353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0003245621919631958, "target_z": -0.4531249924015521, "ce": 6.181467056274414, "genuineness": 4.143336772918701, "identity": 0.5660185217857361, "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_Disgust/4beec27579fb6d6e2f3490befcbdd476f289a86695bc8fcd794c58911043619e.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "4c1ff15c3a7f5b386d7cbdc432e98b1bfaeffd03def58909f31745375639e21a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "860e7ec63ce6f42e4a896993f16e109373f45e7de61dac7dcb9028a7f6308cff", "generation_seconds_batch": 16.491173104033805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03797776997089386, "target_z": -0.5312499848031041, "ce": 6.197352409362793, "genuineness": 4.607763767242432, "identity": 0.7238222360610962, "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_Disgust/4c1ff15c3a7f5b386d7cbdc432e98b1bfaeffd03def58909f31745375639e21a.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "4cba7185d8b9ca63f058dfe6763b21bb99908243af2b445c9ce5b90aaf05b64a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7112e3735157a1f2f6bb49f82f564346381beb599cccd5013f91e18e4fde3307", "generation_seconds_batch": 18.848381652031094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.049468472599983215, "target_z": -0.5546874886023281, "ce": 6.229123115539551, "genuineness": 4.406930446624756, "identity": 0.6411978006362915, "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_Disgust/4cba7185d8b9ca63f058dfe6763b21bb99908243af2b445c9ce5b90aaf05b64a.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": "4d6fe10fc32e6b5bdb6fed97a2266c0a4f5153ad908f466414355521965a5c9f", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e030ba98b48a1ed2102cd0cd8b380e18a7e284487432a7d2444ff3bedb4ab6fe", "generation_seconds_batch": 19.308333867928013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12767982482910156, "target_z": -0.19335937594980598, "ce": 6.221180438995361, "genuineness": 4.406930446624756, "identity": 0.5142166614532471, "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_Disgust/4d6fe10fc32e6b5bdb6fed97a2266c0a4f5153ad908f466414355521965a5c9f.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "4d93221230ece45fb058cddaad3c33eb8c53a7db28c2d09a0532924a4335e9c5", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ab4a99f6e80b3b965f1ec93e62dc7465b2baec89ef7f05529683aecb5de1542c", "generation_seconds_batch": 16.68964495405089, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.013081252574920654, "target_z": -0.4804687367027161, "ce": 6.435632705688477, "genuineness": 4.3127899169921875, "identity": 0.5367437601089478, "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_Disgust/4d93221230ece45fb058cddaad3c33eb8c53a7db28c2d09a0532924a4335e9c5.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "4da3bd0c6fdedf081fcb2242544232879279db9ad96de92c8ef925819c966d56", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc24539638e249a113f6ed3c85e37a3ef50644c00b4f9be990aaca0999e068b5", "generation_seconds_batch": 19.00080578692723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32780951261520386, "target_z": 0.21484371390737236, "ce": 6.213237762451172, "genuineness": 4.406930446624756, "identity": 0.6612157821655273, "hypothesis": "Die Tür 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_Disgust/4da3bd0c6fdedf081fcb2242544232879279db9ad96de92c8ef925819c966d56.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "4ec5c78e924d97652d882e248f6c44f1ba0a7778a8151c068ac11bf5bf78a252", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4dae57228b04864e942773c9b3e5eabbe53433d711c48c146ec9c56edf62c5b5", "generation_seconds_batch": 19.54892632504925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08075946569442749, "target_z": -0.28906249620077606, "ce": 6.38003396987915, "genuineness": 4.444586753845215, "identity": 0.37101811170578003, "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_Disgust/4ec5c78e924d97652d882e248f6c44f1ba0a7778a8151c068ac11bf5bf78a252.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "4f1970267c4577fbda6289546b8f205535c3c5f8ee212d9ed1aa86e6ab8f3baa", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ecca81ab31c8eeeae1518eacc10669137dc3785d16c0422d383151972517482a", "generation_seconds_batch": 19.921228746999986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04532980918884277, "target_z": -0.3613281126525221, "ce": 6.149696350097656, "genuineness": 3.810706615447998, "identity": 0.23250868916511536, "hypothesis": "The 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_Disgust/4f1970267c4577fbda6289546b8f205535c3c5f8ee212d9ed1aa86e6ab8f3baa.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "4f1d62179c979eb06cb8c4ee9c6048ed5f9a8e5e8ee28259216151f740ee8d97", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78e47d1964c45a07d24d9abe1b34874c29e6f1cd90cac6b2b8b9d0af26a189d5", "generation_seconds_batch": 18.839402387966402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03223241865634918, "target_z": -0.5195312329034921, "ce": 6.038498878479004, "genuineness": 4.168440818786621, "identity": 0.8088806867599487, "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_Disgust/4f1d62179c979eb06cb8c4ee9c6048ed5f9a8e5e8ee28259216151f740ee8d97.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": "4f401abe2ffe33d3a2a237f7e1e8d34a6f88fe9f7f9fb2319a6c8114f9ffd55e", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "403321c1d24ccfb56f3733904433ed47fbf746cde1853110823092ed320a01de", "generation_seconds_batch": 13.68820621795021, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16885483264923096, "target_z": -0.10937500759844793, "ce": 6.252951145172119, "genuineness": 4.042920112609863, "identity": 0.385744571685791, "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_Disgust/4f401abe2ffe33d3a2a237f7e1e8d34a6f88fe9f7f9fb2319a6c8114f9ffd55e.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "4f9bdfdd9eb74cb9f80bdb1dc5cf31a8a9a8bb22296736c590cb169f48e318f2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e8b227b0d185c66f97397ddba009e1ea8a96588e46411437557ddf5e661db74e", "generation_seconds_batch": 18.860652763978578, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13917052745819092, "target_z": -0.16992187215058202, "ce": 6.260893821716309, "genuineness": 3.8420867919921875, "identity": 0.3163771629333496, "hypothesis": "The 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_Disgust/4f9bdfdd9eb74cb9f80bdb1dc5cf31a8a9a8bb22296736c590cb169f48e318f2.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "4fe9fd0f076d5d8ed55496dfee6e1ea6816aec03e3804bbef217944435bf7e59", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b440edf737990c3b5c32fd4015190639bcf263e2836f623ffa4450b30a26cc4b", "generation_seconds_batch": 13.717075331951492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22822345793247223, "target_z": 0.01171875189961198, "ce": 6.173524379730225, "genuineness": 3.9173994064331055, "identity": 0.6138375997543335, "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_Disgust/4fe9fd0f076d5d8ed55496dfee6e1ea6816aec03e3804bbef217944435bf7e59.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "505d0e7a6192055b16a3e6babc62b4f3a9c73c6eb99b5ade2b5e80bebaad2798", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "829158d1c70a2f52d9f5095ab0cc6bf9b967544456a038030c17a6f4af80e4ee", "generation_seconds_batch": 18.78801407001447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.019784167408943176, "target_z": -0.494140624050194, "ce": 6.054384231567383, "genuineness": 4.494794845581055, "identity": 0.6665623188018799, "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_Disgust/505d0e7a6192055b16a3e6babc62b4f3a9c73c6eb99b5ade2b5e80bebaad2798.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "5069bb420f822fafd098a0fa17f81e1adff9991d5f6b8687c8b62dbb7ca6994f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2e14faab4d0f440c39091014a7d70ddd9ff352190d00129a0f25753dae6b42c3", "generation_seconds_batch": 22.67110387806315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1449158787727356, "target_z": -0.15820312025097005, "ce": 6.062326908111572, "genuineness": 4.457139015197754, "identity": 0.3571431636810303, "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_Disgust/5069bb420f822fafd098a0fa17f81e1adff9991d5f6b8687c8b62dbb7ca6994f.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": "516b6c560e34412bb1e2d263528946b8936b336b0a4d30dca75683318a4dab98", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5cefee1c2de9f0490498e8d2be21ae1defca4c83d33528cc8ee4870697a30c7b", "generation_seconds_batch": 13.632788104005158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.122583031654358, "target_z": 1.8359375645868072, "ce": 5.824047088623047, "genuineness": 3.7040140628814697, "identity": 0.44198548793792725, "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_Disgust/516b6c560e34412bb1e2d263528946b8936b336b0a4d30dca75683318a4dab98.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "520cad1859bbdb4d695bd4ea41952994300a7576e8edd2e4fd25e095cd1bee8c", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a6e07ad6dfdc843705c11e1fcd67d1dea5035eb0f9cb74f8cba3e7f8b24a8468", "generation_seconds_batch": 14.20583973499015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0003245621919631958, "target_z": -0.4531249924015521, "ce": 6.38003396987915, "genuineness": 4.293961524963379, "identity": 0.5443469285964966, "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_Disgust/520cad1859bbdb4d695bd4ea41952994300a7576e8edd2e4fd25e095cd1bee8c.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": "52ebf4dce6838018bcab74dcd85c8e73f09ba49dc9da2273ffd5ddbff6c887e2", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4866665839130562454c18531784a1c30c4137eb09ef82888da8be4e45647076", "generation_seconds_batch": 13.833165045944043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8005343675613403, "target_z": 3.2187500455906877, "ce": 5.871703147888184, "genuineness": 3.553389072418213, "identity": 0.45904305577278137, "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_Disgust/52ebf4dce6838018bcab74dcd85c8e73f09ba49dc9da2273ffd5ddbff6c887e2.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "52f0195022d78a20cc914df9473261cdf1f0858c5e602098df7f90a1f442e71a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0a2abb3188e0846f6d3e083d3e4012bd5309e0ae709bb81fe588e83e4987a29e", "generation_seconds_batch": 19.31778772198595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08650481700897217, "target_z": -0.27734374430116404, "ce": 6.149696350097656, "genuineness": 4.68307638168335, "identity": 0.7195402979850769, "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_Disgust/52f0195022d78a20cc914df9473261cdf1f0858c5e602098df7f90a1f442e71a.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "5339884210d6659e69da8d22d6c589a310f01b0bffc41990bb79760959603591", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f74f5fd77c74539e750aac1387d6a6d525a49d9f563470f4684860dc9c98b9dd", "generation_seconds_batch": 18.79905984492507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.052990272641181946, "target_z": -0.34570312025097005, "ce": 6.2767791748046875, "genuineness": 4.030367851257324, "identity": 0.21678774058818817, "hypothesis": "The 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_Disgust/5339884210d6659e69da8d22d6c589a310f01b0bffc41990bb79760959603591.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "53791c1422f1ca9aeadb9e447596a8f8991f8137ffe9a30facddb639360a7b0b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dc1feec95f0ecbe3de65ce0b285d6f53ac7cb5706b3b271e8294cfa2984cb515", "generation_seconds_batch": 13.71900565805845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1222739219665527, "target_z": 3.874999908818625, "ce": 6.109982967376709, "genuineness": 3.6663577556610107, "identity": 0.5752183794975281, "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_Disgust/53791c1422f1ca9aeadb9e447596a8f8991f8137ffe9a30facddb639360a7b0b.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "5413007f446c2cf546f61c7cde961c0b740c206ba031f3d5729f8d6e0ad056d5", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "02d1f35f3320dd6e73e4c9355c993cac0e81f4ac71b49b8b275edbead904bbf0", "generation_seconds_batch": 20.262878926936537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01116614043712616, "target_z": -0.47656249620077606, "ce": 6.324435234069824, "genuineness": 4.3504462242126465, "identity": 0.6263216137886047, "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_Disgust/5413007f446c2cf546f61c7cde961c0b740c206ba031f3d5729f8d6e0ad056d5.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "2de25db99479a80935b5c78a2378b24fdc711f960818ad8acaf65d6fbdacdd05", "generation_seconds_batch": 14.181236278964207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.042457133531570435, "target_z": -0.36718748860232814, "ce": 6.356205940246582, "genuineness": 4.099404335021973, "identity": 0.6180948615074158, "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_Disgust/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "546f0c7117bd02780426890bce7f53f3b95c328bc33761e98eb42aa6b2501fc1", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "957e29ffead797ae3b28aa780d859c1797b66dfc118ac6708010e5b534425614", "generation_seconds_batch": 18.711451445007697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04437224566936493, "target_z": -0.36328124810038803, "ce": 6.252951145172119, "genuineness": 4.507347106933594, "identity": 0.6391043663024902, "hypothesis": "Die Tür 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_Disgust/546f0c7117bd02780426890bce7f53f3b95c328bc33761e98eb42aa6b2501fc1.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "548d5e2f2e6e0f36af34b89cc341b6e54d8e8f8e05a5bb3604184daa48e81e36", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "5261dcf594010a6bdf35cdd0a38fd4fdd8965c4f5431d760c55d1c541889932b", "generation_seconds_batch": 18.83066588593647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007985025644302368, "target_z": -0.4375, "ce": 6.046441555023193, "genuineness": 3.6977379322052, "identity": 0.6516241431236267, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/548d5e2f2e6e0f36af34b89cc341b6e54d8e8f8e05a5bb3604184daa48e81e36.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "54f113fa870a2d8e61a4994aa22e986b347f2719496f7dd01415ea613bc0ceb5", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9e3f2c3339ee2278858d631c9c0d20fa05f3f7a4e105598c795285c74f64c9d7", "generation_seconds_batch": 13.833655451075174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13629785180091858, "target_z": -0.17578124810038803, "ce": 6.2767791748046875, "genuineness": 4.055472373962402, "identity": 0.6001632213592529, "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_Disgust/54f113fa870a2d8e61a4994aa22e986b347f2719496f7dd01415ea613bc0ceb5.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": "554566421125591aba4d539d3b5f3e6dd077bb477dbc04271c8ba86f7f5d9b32", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Escribí el número en el sobre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4ca7507c95d5ef9f3d20eedb2e39752ef7b48b83e9dd0a203ef22339f83a7cfe", "generation_seconds_batch": 13.709977115970105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3306822180747986, "target_z": 0.22070315064476173, "ce": 6.133810997009277, "genuineness": 4.162164688110352, "identity": 0.4015069603919983, "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_Disgust/554566421125591aba4d539d3b5f3e6dd077bb477dbc04271c8ba86f7f5d9b32.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "5597a3d1239c87f68569f99cfceabf7533b31d910517ed181cf3bc8f8192a1f5", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ac46e01a094824e5921272275e61c8b0af01d2dc3ef2c33ccee0cbbe038aa772", "generation_seconds_batch": 21.177830273984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08458970487117767, "target_z": -0.28124998480310415, "ce": 6.070269584655762, "genuineness": 4.256305694580078, "identity": 0.7700944542884827, "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_Disgust/5597a3d1239c87f68569f99cfceabf7533b31d910517ed181cf3bc8f8192a1f5.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": "559cfc696889dbe002369c0ae190faab10cf306b63be8614dfd3b486e29626d2", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8b680e295e7598c976d493e5d693117b8e1e86e1848aeae08d29586d7b5b6195", "generation_seconds_batch": 13.674361295998096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8544666171073914, "target_z": 1.2890624354131928, "ce": 6.252951145172119, "genuineness": 4.111956596374512, "identity": 0.44086936116218567, "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_Disgust/559cfc696889dbe002369c0ae190faab10cf306b63be8614dfd3b486e29626d2.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "55bd09c725068d6246f78431f82a98060c6a87954dad8b0d74b4f0d1625359fa", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "f8892cf9c67d1aa63ebda84909b78917b521aa4eab41001954429d455460c004", "generation_seconds_batch": 15.911037743091583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.08011035621166229, "target_z": -0.6171875189961198, "ce": 6.332377910614014, "genuineness": 4.306513786315918, "identity": 0.4240671992301941, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/55bd09c725068d6246f78431f82a98060c6a87954dad8b0d74b4f0d1625359fa.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "567fad2d4b863e21f589f9ffaf0ac88a56a3141925e263d83eee214f9ba80bce", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f217fab322d72f326b2351af04773489b0c5b336f27f546bc9b9465d8bfbf8fe", "generation_seconds_batch": 18.87537111598067, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06543852388858795, "target_z": -0.32031251139767186, "ce": 6.229123115539551, "genuineness": 4.011539936065674, "identity": 0.1252090036869049, "hypothesis": "The 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_Disgust/567fad2d4b863e21f589f9ffaf0ac88a56a3141925e263d83eee214f9ba80bce.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "5694d8faebaf37ab6b5379604b8c75e0ee15e63d14dddd2009c219c5cc134fb0", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e1c1ba6511bb509e0a208cbf149968c3a7e857a2771d3beb43a01c2012312c03", "generation_seconds_batch": 13.833655451075174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5863503217697144, "target_z": 0.7421875493899115, "ce": 6.046441555023193, "genuineness": 3.9801597595214844, "identity": 0.5923364162445068, "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_Disgust/5694d8faebaf37ab6b5379604b8c75e0ee15e63d14dddd2009c219c5cc134fb0.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "56ca48d7d7cc041febb4b5bd05fae333a75fd2be2652c2698304d62c8e673e87", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "1b706577008e45e6f156740aeda4e7dcc29f22a01306829e021bf95d317bd691", "generation_seconds_batch": 18.99888477602508, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03414754569530487, "target_z": -0.5234375037992239, "ce": 5.998785495758057, "genuineness": 4.162164688110352, "identity": 0.5969762802124023, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/56ca48d7d7cc041febb4b5bd05fae333a75fd2be2652c2698304d62c8e673e87.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "56f771add33d09fd262116f9dfa508c5fadfa4d82db86654aee6ab4384d0a1bf", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0d3d6ccfecf99ee28798b0edfb84a0a88f69fc77f3d0df0afef7a35840b55fa7", "generation_seconds_batch": 18.638018390047364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7127479910850525, "target_z": 0.9999999696062083, "ce": 6.086154937744141, "genuineness": 4.105680465698242, "identity": 0.49986815452575684, "hypothesis": "Die Tür 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_Disgust/56f771add33d09fd262116f9dfa508c5fadfa4d82db86654aee6ab4384d0a1bf.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "571774213405254200a6dbb2cecab129971e040fba85e7949de7b95a24e0c848", "bucket": "emo_Disgust", "phase": "wording", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b71bfdc9eba0a4d9d2336d2ed7838ad0fbe3dd25ca0e3e519acd1a57754c3239", "generation_seconds_batch": 13.933772362070158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10134696960449219, "target_z": -0.247070312025097, "ce": 6.395919322967529, "genuineness": 4.582659721374512, "identity": 0.7336419820785522, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. J'ai posé ton manteau.", "wer": 0.2222222222222222, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/571774213405254200a6dbb2cecab129971e040fba85e7949de7b95a24e0c848.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "572a45985ade9373e18a428ce63f9d8bcf8ff2da79b5d3e1261f4b19eaccdaf9", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "51f280272fca217b0607d6bb1b21211838ca6dafe9e836d8aa863d4cedc97781", "generation_seconds_batch": 21.063440139987506, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.07053475081920624, "target_z": -0.5976562253050443, "ce": 6.332377910614014, "genuineness": 4.645420074462891, "identity": 0.579059362411499, "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_Disgust/572a45985ade9373e18a428ce63f9d8bcf8ff2da79b5d3e1261f4b19eaccdaf9.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "57f03974be94c619328c428537d6e9c3cc2d316a54240961e457c15fde8a6228", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fbf863bc0949d818f05b1794c6a8f0be15ef2a867b0d248bf4b3e7cdf8697516", "generation_seconds_batch": 13.798201110912487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5403875112533569, "target_z": 0.6484375341930156, "ce": 6.078212261199951, "genuineness": 4.231201171875, "identity": 0.6148824691772461, "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_Disgust/57f03974be94c619328c428537d6e9c3cc2d316a54240961e457c15fde8a6228.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": "5835031b6c63da7f084e7e3d4030222f46d4ae49e23a0469900ad4259fbf505c", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e9da8ec7b64c3e21308b8ba964e423e6920ef10230f6584a9dcc316626af0296", "generation_seconds_batch": 13.644241719972342, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04820248484611511, "target_z": -0.3554687367027161, "ce": 6.062326908111572, "genuineness": 4.381826400756836, "identity": 0.6668150424957275, "hypothesis": "Alguien ha movido la pequeña sillazón. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "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_Disgust/5835031b6c63da7f084e7e3d4030222f46d4ae49e23a0469900ad4259fbf505c.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": "58ecde1cea6e18fcd5c63382d0fe2b7311f78b7bef7a5f6b061e1bd7e9a49290", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8f78b496358c0864e74df63a7e3066cbb7015dd25c9b54c07afa5f96b063e462", "generation_seconds_batch": 13.593758465955034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10086818784475327, "target_z": -0.24804687974902995, "ce": 6.229123115539551, "genuineness": 4.268857479095459, "identity": 0.6665672063827515, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/58ecde1cea6e18fcd5c63382d0fe2b7311f78b7bef7a5f6b061e1bd7e9a49290.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "590ee37c5eecc5777a375b2267d51d97af6abc9a3a4d1f03f5a0bc52c653330e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2cef5fc5c1351c88c70f850dfe359b023da82d296de8d7b2536e62eb39c03df7", "generation_seconds_batch": 22.249193405965343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05490538477897644, "target_z": -0.34179687974902995, "ce": 6.332377910614014, "genuineness": 4.469690799713135, "identity": 0.6012289524078369, "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_Disgust/590ee37c5eecc5777a375b2267d51d97af6abc9a3a4d1f03f5a0bc52c653330e.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "5986fc1e0b476536f062eac57f71c22e1eaef19e06dccb7df035935a57ec63e4", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "b41be3a25ef2ff7b261ec76323fdf89d827203036476314f65c2e834efe08364", "generation_seconds_batch": 21.38089499704074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0520327091217041, "target_z": -0.34765625569883596, "ce": 6.252951145172119, "genuineness": 4.519899368286133, "identity": 0.7251484394073486, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/5986fc1e0b476536f062eac57f71c22e1eaef19e06dccb7df035935a57ec63e4.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "5a11474779258de124dc604808bc42dc258e5087d73971cd8b8b6df148296666", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "32d11f4180d19b5dd3daf7edd9f089c9feba1c58a43a8118d0b2e425f3bb03a7", "generation_seconds_batch": 16.276912022032775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11618912220001221, "target_z": -0.21679687974902995, "ce": 6.109982967376709, "genuineness": 4.557555198669434, "identity": 0.7364847660064697, "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_Disgust/5a11474779258de124dc604808bc42dc258e5087d73971cd8b8b6df148296666.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": "5a1dabf13bee42abef50ce3a159e073a4854d51e248a8251a6e364392202f78f", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2b97894c1401c4449c2bfb5655fc9457c4aa0fbeae52952d537a2a0648b2a225", "generation_seconds_batch": 13.694621996954083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04149957001209259, "target_z": -0.369140624050194, "ce": 6.475345611572266, "genuineness": 4.582659721374512, "identity": 0.4213433265686035, "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_Disgust/5a1dabf13bee42abef50ce3a159e073a4854d51e248a8251a6e364392202f78f.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "5a279cbbf19b5b36bb2d3dff217ce522676d62a70546b2f0461d9d32fe5e552b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2cf438b2f95b9b1e9ce3b28576bf61a873c32828a56d126144ab09cac9832a49", "generation_seconds_batch": 18.95612774603069, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06065073609352112, "target_z": -0.330078127849418, "ce": 6.205295085906982, "genuineness": 4.143336772918701, "identity": 0.4305471181869507, "hypothesis": "The 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_Disgust/5a279cbbf19b5b36bb2d3dff217ce522676d62a70546b2f0461d9d32fe5e552b.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "5cd522fcbe706c28ad11cdfad0604a776a05390956c9965a11e45f5751e36fac", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bd1d23c9873761c7e9a238acb0a447cbf44e1de2383bde2f755c8fd0982d5c01", "generation_seconds_batch": 19.825216441066004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06543852388858795, "target_z": -0.32031251139767186, "ce": 6.205295085906982, "genuineness": 4.482243061065674, "identity": 0.4846232831478119, "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_Disgust/5cd522fcbe706c28ad11cdfad0604a776a05390956c9965a11e45f5751e36fac.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "5d580e2c1279da01986c542c902fd3781d0709e42a735ac5ce9d28617e6b31a1", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "dba7e8e3ae0da4071088b8ce7aacbe9aee930e384a6e32f8a1605e3a147a01ca", "generation_seconds_batch": 13.892647490021773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.015953928232192993, "target_z": -0.4863281126525221, "ce": 6.2767791748046875, "genuineness": 3.873466968536377, "identity": 0.5747945308685303, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/5d580e2c1279da01986c542c902fd3781d0709e42a735ac5ce9d28617e6b31a1.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "5df8a23ba6c884de34de2fd9fa695dd54a8646fc695c4513f22db13b175c9c42", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "510cccc5859f46ef66bee7080b4c0ce808ffdccb25990d81cfd027681672d185", "generation_seconds_batch": 19.14165495103225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05107516050338745, "target_z": -0.34960936075291016, "ce": 6.2767791748046875, "genuineness": 4.3127899169921875, "identity": 0.5540146231651306, "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_Disgust/5df8a23ba6c884de34de2fd9fa695dd54a8646fc695c4513f22db13b175c9c42.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "d3e1db2b9998222491319512ea879ef118a1316b589a94e538b09e706acc9b7e", "generation_seconds_batch": 13.692619667970575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05011759698390961, "target_z": -0.35156249620077606, "ce": 6.125868320465088, "genuineness": 4.457139015197754, "identity": 0.7842926383018494, "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_Disgust/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.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": "5e0b2fa7c9e1049ba21807d77856d1b0c27662cd1caab2ec6744204ce9566df5", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I wrote the number on the envelope.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9c77e4837cad18231a24c9ee6f6d50cbd4a5bf0774b1906f4f39dd0d2392e6bc", "generation_seconds_batch": 13.649958439986221, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29716765880584717, "target_z": 0.15234374430116407, "ce": 5.935244083404541, "genuineness": 3.390212059020996, "identity": 0.456811785697937, "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_Disgust/5e0b2fa7c9e1049ba21807d77856d1b0c27662cd1caab2ec6744204ce9566df5.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "5e2909b4f6f7271d0baafa7d0336151fafa61326dcc660dd567cc55eadae65ba", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "fe6a0b90139f0c641073c3ec5fca1301865ded90b3b4d8c538276ac0656d8fff", "generation_seconds_batch": 19.353109369054437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03862689435482025, "target_z": -0.375, "ce": 6.205295085906982, "genuineness": 4.369274139404297, "identity": 0.7298505306243896, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/5e2909b4f6f7271d0baafa7d0336151fafa61326dcc660dd567cc55eadae65ba.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "5e78832f1b22e920bb3606065039d9549fc1c5b4399347d9c5f8cf1a2c528b4f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "33b10bf7fe4e5fe2d7ffe5db98f1d4e4a156e78f63dd6a2d7b9ae4b73c063fed", "generation_seconds_batch": 18.680003194953315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23492637276649475, "target_z": 0.025390639247089855, "ce": 6.149696350097656, "genuineness": 3.3713839054107666, "identity": 0.3795683979988098, "hypothesis": "The 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_Disgust/5e78832f1b22e920bb3606065039d9549fc1c5b4399347d9c5f8cf1a2c528b4f.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "5fa8386ee957a585db838e37f768eb3a8fb8edd8e330fe7d107bb5ce9595d114", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "deac47165827d905c5575486ae4d7d98cbd73bb41e0ed673b15a61b8c8a47ec2", "generation_seconds_batch": 18.788466191035695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01468794047832489, "target_z": -0.4238281126525221, "ce": 6.141753673553467, "genuineness": 4.413206577301025, "identity": 0.6956210136413574, "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_Disgust/5fa8386ee957a585db838e37f768eb3a8fb8edd8e330fe7d107bb5ce9595d114.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "60214bd75756f2d56d969f1baacc645e5bbb21b9dc83ac936b4462e17799ddf4", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "502aceeaddef0bd997804ca820dfd834ede4014f66a8a28bab0e5b5dd9b826a4", "generation_seconds_batch": 13.648610713076778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00733591616153717, "target_z": -0.46875001519689585, "ce": 6.348263263702393, "genuineness": 4.344170093536377, "identity": 0.44703546166419983, "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_Disgust/60214bd75756f2d56d969f1baacc645e5bbb21b9dc83ac936b4462e17799ddf4.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "60560091d61a364f4b6d3d3d1c9cf6471b8fb6544cfc1a9e4ac23de79ad7dcaa", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f6322619a38b6b36bf54c335dbefed530e71edda132a25ffb79ff05bcc691f51", "generation_seconds_batch": 18.788483090000227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01756061613559723, "target_z": -0.4179687367027161, "ce": 6.229123115539551, "genuineness": 4.2374773025512695, "identity": 0.5616905093193054, "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_Disgust/60560091d61a364f4b6d3d3d1c9cf6471b8fb6544cfc1a9e4ac23de79ad7dcaa.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "609614109f99e2b1b064c15b85a985e2d91a2ed3cfe7439bb134197ad023dfab", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6bb7f90459dc879709a2ccda7aa22284b003a375e228c983c45a4f0af86ebe02", "generation_seconds_batch": 18.813863064046018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06160829961299896, "target_z": -0.3281249924015521, "ce": 6.173524379730225, "genuineness": 4.482243061065674, "identity": 0.4336881637573242, "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_Disgust/609614109f99e2b1b064c15b85a985e2d91a2ed3cfe7439bb134197ad023dfab.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "60bf48e376ec24c5dd2ae82ba194529468f706e112721652ae84a0b7079c0751", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "777a99f4e4ddf36ad56f5299cefc6ef9404303cbb900fb57fb1ffd8e4b2fbfc0", "generation_seconds_batch": 15.798123402055353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17076995968818665, "target_z": -0.10546873670271613, "ce": 5.728734970092773, "genuineness": 3.9425034523010254, "identity": 0.34161239862442017, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.", "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_Disgust/60bf48e376ec24c5dd2ae82ba194529468f706e112721652ae84a0b7079c0751.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "613e75c28faab455315a48bcdaca8142c09d5b5ab848c7444ba15df33bf65eeb", "bucket": "emo_Disgust", "phase": "wording", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "09b683226a703c6abef19dc25b8f99ac6d14d321dfe87589a83f2e3aa00edcaa", "generation_seconds_batch": 14.009236710029654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.053947821259498596, "target_z": -0.34375001519689585, "ce": 6.300607204437256, "genuineness": 4.413206577301025, "identity": 0.6347227096557617, "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_Disgust/613e75c28faab455315a48bcdaca8142c09d5b5ab848c7444ba15df33bf65eeb.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": "614cd4fc80f64ab37bc28bf3ee402dabc276bea8d7832eb7ac32f95348734b6f", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9ceb1d90f4612c818822c399b247218703a28029318bc4aa3d61530c0856225d", "generation_seconds_batch": 18.54399111389648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.225999355316162, "target_z": 2.046875098779823, "ce": 6.070269584655762, "genuineness": 3.7542223930358887, "identity": 0.5682227611541748, "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_Disgust/614cd4fc80f64ab37bc28bf3ee402dabc276bea8d7832eb7ac32f95348734b6f.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "61762678cb5781fa96b1809631c81f0c8b2fb3210707ca1a283354c12de8556b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "ff6f6a43dd00433eee6702617330ae1ed18fde865807698f5b022d4771a31fe1", "generation_seconds_batch": 18.76773109298665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14012807607650757, "target_z": -0.16796876709650782, "ce": 6.117925643920898, "genuineness": 3.8295347690582275, "identity": 0.6263923645019531, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/61762678cb5781fa96b1809631c81f0c8b2fb3210707ca1a283354c12de8556b.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "6182c9f657b01cccc28ee527fe103e155c81fc663b2edead2777513e5a7f0d1c", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7b21fe1ee39bad907b55a9009114ac368b4936780803cd342c3bcda5de288e91", "generation_seconds_batch": 18.769624685985036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03223241865634918, "target_z": -0.5195312329034921, "ce": 6.4912309646606445, "genuineness": 4.400654315948486, "identity": 0.614693284034729, "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_Disgust/6182c9f657b01cccc28ee527fe103e155c81fc663b2edead2777513e5a7f0d1c.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "61a39cc7048cb63400805529cfa70698de686a74f4dcabe3c610e7f349853571", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eef2cd84fd5abbd29d26648c5ffdf3b53138d963163025e20fe4c2a5e61edd12", "generation_seconds_batch": 18.919475527014583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03797776997089386, "target_z": -0.5312499848031041, "ce": 6.419747352600098, "genuineness": 4.381826400756836, "identity": 0.28727519512176514, "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_Disgust/61a39cc7048cb63400805529cfa70698de686a74f4dcabe3c610e7f349853571.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "61d5c77b035ece606c80461456f0e98d344742aa5923a2cb06c21d0486908a85", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "0e4a1f5a0604e9f75d10a24dc790876812683eab51aaa109cd55b3d939e1bf41", "generation_seconds_batch": 19.030609612935223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25120484828948975, "target_z": 0.05859372910426821, "ce": 6.133810997009277, "genuineness": 4.017816066741943, "identity": 0.6125345826148987, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/61d5c77b035ece606c80461456f0e98d344742aa5923a2cb06c21d0486908a85.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "620980d0053a1c7c30b7e7439ca5920ece0a456fa882aa56b2fd2718de4488e6", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "14cccdc7428ec1b88815d1465315286cc83dd6838632b2511f63cef01b61b932", "generation_seconds_batch": 18.854214902035892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.039584457874298096, "target_z": -0.3730468645521341, "ce": 6.24500846862793, "genuineness": 3.8169827461242676, "identity": 0.32846641540527344, "hypothesis": "The 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_Disgust/620980d0053a1c7c30b7e7439ca5920ece0a456fa882aa56b2fd2718de4488e6.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "6245fcc58cc38728884619f982a78b39c9e42443176bbee2f66762a2d3e452b3", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4472b6382eb1640610016505b887117cbcfd73a90ab5225ae912d8d61ab1ba7a", "generation_seconds_batch": 13.582637815037742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6090227365493774, "target_z": 2.8281251443705107, "ce": 5.967014789581299, "genuineness": 3.8922953605651855, "identity": 0.5905776023864746, "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_Disgust/6245fcc58cc38728884619f982a78b39c9e42443176bbee2f66762a2d3e452b3.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": "62563f10e92ba933a85465dda267f8c86c24c69dc48ea942dc8e57d13c022263", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9fbc225095b9c327db0c33beedb2ccc8b6e5e3b321d1fda84fa9bd8ae4e55d84", "generation_seconds_batch": 13.714193867053837, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5327270030975342, "target_z": 0.6328124506100885, "ce": 6.197352409362793, "genuineness": 4.281409740447998, "identity": 0.49033254384994507, "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_Disgust/62563f10e92ba933a85465dda267f8c86c24c69dc48ea942dc8e57d13c022263.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "629253b5a837f364d4d039069f1ca4761dc3cffbaff7f9dc463cad7582ab4bd8", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6f96d01ff1cb57de85ffa6dd58bddc78af149ce2ebf9c84d9ebea7141dd3f455", "generation_seconds_batch": 18.58571719797328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7510503530502319, "target_z": 1.0781250227953438, "ce": 6.268836498260498, "genuineness": 4.18099308013916, "identity": 0.5338979959487915, "hypothesis": "Die Tür 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_Disgust/629253b5a837f364d4d039069f1ca4761dc3cffbaff7f9dc463cad7582ab4bd8.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "62db6475f3bbb61a70905a84ac8a139bb3d6ed24d0507c80d4bcec2425241fa9", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0077c27e3381df776a0fbc01fb89d96f7185573a153f1758814b2773d8ccc83b", "generation_seconds_batch": 19.990994245978072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09895307570695877, "target_z": -0.25195312025097005, "ce": 6.41180419921875, "genuineness": 4.582659721374512, "identity": 0.5462589859962463, "hypothesis": "Die Tür 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_Disgust/62db6475f3bbb61a70905a84ac8a139bb3d6ed24d0507c80d4bcec2425241fa9.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "6314e2db1fb0d7b2875ea130fb1d9dcbdcf79d0b7ed6f438822209ec45360692", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c549b00b2884d8e253a3b7395576f90d542260c6fe9fae4c29bed0c228629420", "generation_seconds_batch": 18.831923750927672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17460018396377563, "target_z": -0.09765625569883594, "ce": 6.109982967376709, "genuineness": 4.005263805389404, "identity": 0.7056323885917664, "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_Disgust/6314e2db1fb0d7b2875ea130fb1d9dcbdcf79d0b7ed6f438822209ec45360692.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "63c3fa2beb2efee1164e8e20aedaafb094e75d66f9bcbd9bd6d3ac4bf4dc8988", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "51623eb7df5ccae9b2f3cf79c56bc51cbb2b990826fde1e78cf0c737dda9d912", "generation_seconds_batch": 18.809750888030976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02809375524520874, "target_z": -0.3964843683513581, "ce": 6.117925643920898, "genuineness": 3.7793264389038086, "identity": 0.21093407273292542, "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_Disgust/63c3fa2beb2efee1164e8e20aedaafb094e75d66f9bcbd9bd6d3ac4bf4dc8988.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "63d88ea566dfde66456414b3d9e8881e9b279e4818037827842d7fbb9816ac41", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cdf3c67324b5a46bccc435fbd3616691a1c9d977848bdf6b27876fc4d2935302", "generation_seconds_batch": 19.382100368035026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.053947821259498596, "target_z": -0.34375001519689585, "ce": 6.229123115539551, "genuineness": 4.2374773025512695, "identity": 0.6617218255996704, "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_Disgust/63d88ea566dfde66456414b3d9e8881e9b279e4818037827842d7fbb9816ac41.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": "641b251016c0034a953ac9eae86cfad416061a88dc791f56972982dcf29faaec", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bb31c5ee6608d43b09b4c8306e3dba6c63498a121b6fa1a2a3040abae37063d8", "generation_seconds_batch": 18.617334779002704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9920461177825928, "target_z": 3.609375189961198, "ce": 6.125868320465088, "genuineness": 3.798154592514038, "identity": 0.6927198171615601, "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_Disgust/641b251016c0034a953ac9eae86cfad416061a88dc791f56972982dcf29faaec.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "6449c7312e9cfd5bbec7eae16fd27dc4acd9fb203e2b1d536b23de8cc32e2c90", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a8693738f9d7190f51061ccceab22fb838dfe871ae4c05535a44b351f6c43932", "generation_seconds_batch": 18.69804521801416, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.058735623955726624, "target_z": -0.3339843683513581, "ce": 5.982900142669678, "genuineness": 4.356721878051758, "identity": 0.5095354318618774, "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_Disgust/6449c7312e9cfd5bbec7eae16fd27dc4acd9fb203e2b1d536b23de8cc32e2c90.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "645467b52a32dcaff31be65390fcefe87e1354cd528185d0a4e7fd9cc3d6e824", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "adda3413f39aa082b690ddbe65634c04ecd8052cbec803b227aee9bde252e52b", "generation_seconds_batch": 22.975545894005336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01851816475391388, "target_z": -0.4160156316486419, "ce": 6.395919322967529, "genuineness": 4.293961524963379, "identity": 0.5359104871749878, "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_Disgust/645467b52a32dcaff31be65390fcefe87e1354cd528185d0a4e7fd9cc3d6e824.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "6459b4fb5c52df5afafb911d1bc7d52d1cf0505f9b0ca56d673dc14afd8493d6", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6fd66c57bb2c40cff22cf3b373e66e509946ee61cc54a5c53cc3b701adc41fd1", "generation_seconds_batch": 14.12661617307458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14970366656780243, "target_z": -0.14843750379922396, "ce": 6.324435234069824, "genuineness": 4.519899368286133, "identity": 0.6148285865783691, "hypothesis": "Die Tür 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_Disgust/6459b4fb5c52df5afafb911d1bc7d52d1cf0505f9b0ca56d673dc14afd8493d6.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "648c28170508c3b884f4ab48cb3b68512ef29841ded23c317584f7cb9a3528ea", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2b680345e15928dea64a456a2bf0d0d7aaccfa9b7ed96c3da1ab89817a322a2d", "generation_seconds_batch": 20.595729092950933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02809375524520874, "target_z": -0.3964843683513581, "ce": 6.062326908111572, "genuineness": 4.607763767242432, "identity": 0.5679117441177368, "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_Disgust/648c28170508c3b884f4ab48cb3b68512ef29841ded23c317584f7cb9a3528ea.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "64b589b5d3a4f8395298112e1e81acbc368439f0d6274e77c7b29899f9baf13d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "44ab3dc52b0142e5be858765ead48b721e71b786a504f7f06e2e8cf0a59dece5", "generation_seconds_batch": 19.716223273891956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05712895095348358, "target_z": -0.5703125113976719, "ce": 6.427689552307129, "genuineness": 4.406930446624756, "identity": 0.38900935649871826, "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_Disgust/64b589b5d3a4f8395298112e1e81acbc368439f0d6274e77c7b29899f9baf13d.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "64bc234b1d803d8e87f1c14f4e3e098d634ee22a53a67cd7209ea9bf9c760aea", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e54e43aafff5642ddce1511f608ac3ecf45ff48bdf16fc29b8debf955507b2fb", "generation_seconds_batch": 18.866027421085164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0003245621919631958, "target_z": -0.4531249924015521, "ce": 6.046441555023193, "genuineness": 4.457139015197754, "identity": 0.7484414577484131, "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_Disgust/64bc234b1d803d8e87f1c14f4e3e098d634ee22a53a67cd7209ea9bf9c760aea.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "6512d516ad279b01157ef82812c062cea543c736a1f4ab2f725e71cec700ab61", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "df6f6663a63962a9852895ded37c560cabb47aecc0fa6885b910683ad96b7840", "generation_seconds_batch": 14.581261145998724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33834266662597656, "target_z": 0.23632811265252213, "ce": 6.427689552307129, "genuineness": 4.3127899169921875, "identity": 0.6274900436401367, "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_Disgust/6512d516ad279b01157ef82812c062cea543c736a1f4ab2f725e71cec700ab61.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": "6531784cba08b12c7c86534fc5876b9146717b8980f6f908fb7cd5e464c2b854", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0b3a608206b8e29cc023243a7d0e02eb05cc2287807de2186897d31bc7abfd29", "generation_seconds_batch": 18.758354914025404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1181042417883873, "target_z": -0.21289062405019402, "ce": 5.422942161560059, "genuineness": 4.017816066741943, "identity": 0.12231496721506119, "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_Disgust/6531784cba08b12c7c86534fc5876b9146717b8980f6f908fb7cd5e464c2b854.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "656533c221c2a1053ddbb33862d6cbd15bed6d0de3badd0616400e2e535bfa88", "bucket": "emo_Disgust", "phase": "wording", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6cc0fafb925f6eecb2a02c1c03c1997e153258cc9d0621d0c16e32762a1de79f", "generation_seconds_batch": 14.196581730036996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.09160105884075165, "target_z": -0.6406250227953437, "ce": 6.427689552307129, "genuineness": 4.1998209953308105, "identity": 0.5730774402618408, "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_Disgust/656533c221c2a1053ddbb33862d6cbd15bed6d0de3badd0616400e2e535bfa88.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "65a61e3a7c9c01e5d9d91536d0c29fa54dbe15963fac6686a61dfb9965955fcf", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5b5ad29f7677a2769aaad48bcea61286b07f5a75e557c66f45d032b62d4c0413", "generation_seconds_batch": 18.859513973002322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0663960874080658, "target_z": -0.318359375949806, "ce": 6.109982967376709, "genuineness": 3.8546390533447266, "identity": 0.3253301978111267, "hypothesis": "The 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_Disgust/65a61e3a7c9c01e5d9d91536d0c29fa54dbe15963fac6686a61dfb9965955fcf.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "66a126a1aa107bd25b5a97aee74f4c7239bc97186c7de1dc1b3448cac7dcce32", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "29a9ed07ea998202dbe906aeb66d8a20b2befa9def545cc2ee83b796f3ec57b1", "generation_seconds_batch": 18.684818823938258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03606267273426056, "target_z": -0.5273437746949557, "ce": 6.213237762451172, "genuineness": 4.494794845581055, "identity": 0.7925752401351929, "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_Disgust/66a126a1aa107bd25b5a97aee74f4c7239bc97186c7de1dc1b3448cac7dcce32.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": "66a544be6864d4c1a4ef722f35b25f1b2383919fba184bb1dd2fd64bd6b5eca0", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "f3315a12b4bde5192b26cd37718123fdc09bd7da9a7a1ea92e2cb0f539b1595b", "generation_seconds_batch": 18.728912401013076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.647325038909912, "target_z": 2.906250075984479, "ce": 5.3514580726623535, "genuineness": 3.785602569580078, "identity": 0.5776850581169128, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zel maar wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/66a544be6864d4c1a4ef722f35b25f1b2383919fba184bb1dd2fd64bd6b5eca0.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "66ca64b1596f2f4a7b38b5b2505e4e8e248d4cd813e3c5f9619e5208e16818f0", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "e3ecece4b42afe668125353b2bee408f3dec93d9ebbfc4a487c5ed1e22e845e2", "generation_seconds_batch": 18.962900861050002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07405655086040497, "target_z": -0.30273438354825394, "ce": 6.324435234069824, "genuineness": 4.400654315948486, "identity": 0.7306949496269226, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/66ca64b1596f2f4a7b38b5b2505e4e8e248d4cd813e3c5f9619e5208e16818f0.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "66ebbcb74522ee8fe0f525e64731108a73040f49af15604dc8e094dbb7dec4a0", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1580c30fa8d575f11df42356e1721d9015821559d11f1533cee5398c3c4d79a1", "generation_seconds_batch": 18.923400352010503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10278330743312836, "target_z": -0.24414062405019402, "ce": 6.221180438995361, "genuineness": 4.068024158477783, "identity": 0.6069296598434448, "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_Disgust/66ebbcb74522ee8fe0f525e64731108a73040f49af15604dc8e094dbb7dec4a0.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "6706cec73e3e9820a524ff2f48dbcd1df78b660d8a354a5613752cc9ceca9300", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "6ec3db906a201e5a5e9729d84cc7db6ae5ae6f675ab8c2339a716d8259542940", "generation_seconds_batch": 19.1083247900242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05521382391452789, "target_z": -0.5664062405019401, "ce": 6.1894097328186035, "genuineness": 4.099404335021973, "identity": 0.37104907631874084, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/6706cec73e3e9820a524ff2f48dbcd1df78b660d8a354a5613752cc9ceca9300.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "67090a54a570663232219b22d2d477b4104847169fe6e53e49fa060a29ea9f97", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e4834c5b047c0a2a47d82ad9fefd64191a581818968594901089c57e80955c0e", "generation_seconds_batch": 19.37031012494117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04820248484611511, "target_z": -0.3554687367027161, "ce": 6.078212261199951, "genuineness": 4.68307638168335, "identity": 0.7525132894515991, "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_Disgust/67090a54a570663232219b22d2d477b4104847169fe6e53e49fa060a29ea9f97.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": "67dfd9480bf51c18a41a744055c869a8aca5d02b6965346c7505ae97769eb640", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "fc98e24b0c7ea66eac1a71bf078a71619efb6c3140e8ca30869cf0d44d64e5cd", "generation_seconds_batch": 13.785327820922248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19087867438793182, "target_z": -0.06445313544786589, "ce": 6.1894097328186035, "genuineness": 4.093128204345703, "identity": 0.5581324696540833, "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": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/67dfd9480bf51c18a41a744055c869a8aca5d02b6965346c7505ae97769eb640.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "682fa326c3f0a3bbc83d23949ea8446f225a05dbfb8ad1f6d44a7d6099d62dd2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2d8614d0e53f3382be3b82c716a83127f2aa22a7c42bba6520568141c4b2a0c4", "generation_seconds_batch": 18.78801407001447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.014996379613876343, "target_z": -0.4843750075984479, "ce": 6.0305562019348145, "genuineness": 4.494794845581055, "identity": 0.5987132787704468, "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_Disgust/682fa326c3f0a3bbc83d23949ea8446f225a05dbfb8ad1f6d44a7d6099d62dd2.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": "687edc335b043931cf03a9ebe4c7be31863255d484345b16fefa5a7088c6e88e", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4720cc2cb5926b296951df363179c913035bd0a5a062b584dd70a342183279c6", "generation_seconds_batch": 18.540502244024538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3562272787094116, "target_z": 2.3125000607875834, "ce": 6.181467056274414, "genuineness": 3.540836811065674, "identity": 0.6078559160232544, "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_Disgust/687edc335b043931cf03a9ebe4c7be31863255d484345b16fefa5a7088c6e88e.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "68eea0c2c775ebc59f68ea4ba0fcac99ef2060ece960a66e821266f695af5026", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "8bb543e4fec51c4191ec5c54e85a7d923cce9c3cbd7f9850aadc34d2017e5a72", "generation_seconds_batch": 18.85114219796378, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03575421869754791, "target_z": -0.380859375949806, "ce": 6.070269584655762, "genuineness": 3.9425034523010254, "identity": 0.7916507720947266, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/68eea0c2c775ebc59f68ea4ba0fcac99ef2060ece960a66e821266f695af5026.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": "69c14487a0a1a98257700b1ddabd8a56c6e1f8aebf3652259ac343c45a9e884b", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I wrote the number on the envelope.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "86b968858df08c8d3cca13d98fc05be5e3503c667d0b550c8e47d1aead367e29", "generation_seconds_batch": 15.12154770793859, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1573641300201416, "target_z": -0.1328125113976719, "ce": 6.284721851348877, "genuineness": 3.380797863006592, "identity": 0.44692492485046387, "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_Disgust/69c14487a0a1a98257700b1ddabd8a56c6e1f8aebf3652259ac343c45a9e884b.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": "6a0abc97b7a0b32158f877de0695889b417e9d5ef443379640293cef2f1220f2", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b882d012eda2a66cc1a47c28486f45ffc583ac8e44045d3bcff166a698d980d4", "generation_seconds_batch": 13.763904200983234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07788679003715515, "target_z": -0.294921872150582, "ce": 6.260893821716309, "genuineness": 4.325342178344727, "identity": 0.8280044794082642, "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_Disgust/6a0abc97b7a0b32158f877de0695889b417e9d5ef443379640293cef2f1220f2.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "31355c6d8768d96a7d537e343813125afe70c4666d2089efa6569a442edc6d07", "generation_seconds_batch": 16.190696337027475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05011759698390961, "target_z": -0.35156249620077606, "ce": 6.395919322967529, "genuineness": 4.068024158477783, "identity": 0.3556906580924988, "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_Disgust/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "6a72bb4f346aa3e537bb088e7b35925626fb0075627f7024dd630a3366dc76e1", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9dab64695ebada933b30607d7867e2f3778007b4bca906d3f6773a134144fcdc", "generation_seconds_batch": 18.95679457404185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05712895095348358, "target_z": -0.5703125113976719, "ce": 6.252951145172119, "genuineness": 4.218649387359619, "identity": 0.4423449635505676, "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_Disgust/6a72bb4f346aa3e537bb088e7b35925626fb0075627f7024dd630a3366dc76e1.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "6a8e949620524c6843bc46eac2ddfbdb466b632a09f5e5a582cd32881ce17f8c", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "700df242f13c3868d969006fcbd0b14268dda863a7df2994dc651a05d3805dbc", "generation_seconds_batch": 15.749064119998366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030008867383003235, "target_z": -0.392578127849418, "ce": 6.332377910614014, "genuineness": 4.6705241203308105, "identity": 0.8080183267593384, "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_Disgust/6a8e949620524c6843bc46eac2ddfbdb466b632a09f5e5a582cd32881ce17f8c.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "6af575b188266536d87101363202d78ecf36ee7e737a2d1127898ab2991477d6", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7a44996bc3d10816fee1b434bef33ceb27a2312e783b794c74161805c6589c50", "generation_seconds_batch": 15.10211687698029, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05904404819011688, "target_z": -0.5742187215058203, "ce": 6.308549880981445, "genuineness": 4.2751336097717285, "identity": 0.592503547668457, "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_Disgust/6af575b188266536d87101363202d78ecf36ee7e737a2d1127898ab2991477d6.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": "6b7662efb4c9f914b1ef9d0d776c2ec82f73f1c44a8e847a3982d9aa4607a6c3", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "313ff5ca33ee3d22c19b17662702d5c4d20309389f90bf7b21f342a7f86a5abc", "generation_seconds_batch": 13.616183253005147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2183388471603394, "target_z": 2.0312500151968957, "ce": 5.982900142669678, "genuineness": 3.8671910762786865, "identity": 0.754403829574585, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/6b7662efb4c9f914b1ef9d0d776c2ec82f73f1c44a8e847a3982d9aa4607a6c3.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "66846cf4cdffc1b4e7c7a142508b2c2681a4dce50ae87ad4d8f24e33cfc2c616", "generation_seconds_batch": 13.678953233058564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06735365092754364, "target_z": -0.3164062405019401, "ce": 6.308549880981445, "genuineness": 4.645420074462891, "identity": 0.6980360746383667, "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_Disgust/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "6c244cd2fc959b6afb42e6d5688664bfa4d8506f5ff17355d38aa30c57c17eed", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f1aa1fd69429154ca57d2d72af3e8c80f7e24534e95d3e59aebf81d50a45b386", "generation_seconds_batch": 18.809353880002163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.002548113465309143, "target_z": -0.4589843683513581, "ce": 6.09409761428833, "genuineness": 4.093128204345703, "identity": 0.617156982421875, "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_Disgust/6c244cd2fc959b6afb42e6d5688664bfa4d8506f5ff17355d38aa30c57c17eed.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "6c6a0574d789895f7087788c535207ce4b170dbe5072c874ee25ff67cb5a64a5", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "75681e9c8115f3cdb801e76673512cc10d90a121e84384e00b54cbca11f0be5e", "generation_seconds_batch": 14.873984358971938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13534030318260193, "target_z": -0.17773435315446223, "ce": 6.268836498260498, "genuineness": 4.557555198669434, "identity": 0.7075917720794678, "hypothesis": "Die Tür 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_Disgust/6c6a0574d789895f7087788c535207ce4b170dbe5072c874ee25ff67cb5a64a5.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "6cc832bf17a5e4fc4baf2cc617ed0edfa9ab2efc41767498b21de25bd44d42d7", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f1f7a540e40798f95f910aecc44d5d208c612418d69427a949841733ea3f0249", "generation_seconds_batch": 21.94266980199609, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04820248484611511, "target_z": -0.3554687367027161, "ce": 6.252951145172119, "genuineness": 4.105680465698242, "identity": 0.6112966537475586, "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_Disgust/6cc832bf17a5e4fc4baf2cc617ed0edfa9ab2efc41767498b21de25bd44d42d7.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "6d03685de3bf264b057fb334deca10c53f28bc998ba6fb89868b756e52ebf4ec", "bucket": "emo_Disgust", "phase": "wording", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "73b1beb140743fcad8123ab990b8e998fd7eed2be2138a9fb43898affaf5816a", "generation_seconds_batch": 14.009236710029654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13917052745819092, "target_z": -0.16992187215058202, "ce": 6.268836498260498, "genuineness": 4.005263805389404, "identity": 0.728053092956543, "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_Disgust/6d03685de3bf264b057fb334deca10c53f28bc998ba6fb89868b756e52ebf4ec.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": "6d5f36bfce8cb4f5ff8bcb745d52500f1381870da99e6b420875cc137bb49ba1", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The keys are on the kitchen table.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "bf6532745039c2a2eca008f2dec47bdec01d3a38787eaa0755e84fc7c8f57a04", "generation_seconds_batch": 13.698188609094359, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10086818784475327, "target_z": -0.24804687974902995, "ce": 6.213237762451172, "genuineness": 3.8671910762786865, "identity": 0.40147727727890015, "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": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/6d5f36bfce8cb4f5ff8bcb745d52500f1381870da99e6b420875cc137bb49ba1.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "6d97d590f5c98936db4aafd61b2a410d6fa5fa64cf4ff912ef183536b2a95d93", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "195f7682d14d5b16e743e1f4cba114c8e7f5f0ab88f4a2fd5bc554a851b962c4", "generation_seconds_batch": 19.00080578692723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1717275083065033, "target_z": -0.10351563164864193, "ce": 6.284721851348877, "genuineness": 4.419482707977295, "identity": 0.5775271654129028, "hypothesis": "Die Tür 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_Disgust/6d97d590f5c98936db4aafd61b2a410d6fa5fa64cf4ff912ef183536b2a95d93.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "6e52812c9408dba00915d21d555f7f22a9303c59ab15678d1895b35567ea57be", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b3e0a46d9481907c6820fd6167dcacd29455b166fe4daa4589779f8758ad7da4", "generation_seconds_batch": 18.68134693603497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07309900224208832, "target_z": -0.30468748860232814, "ce": 6.046441555023193, "genuineness": 4.362998008728027, "identity": 0.5927214622497559, "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_Disgust/6e52812c9408dba00915d21d555f7f22a9303c59ab15678d1895b35567ea57be.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": "6e7d18e9b11ed19e9b4f30e8fb99123f45cefd6dd5cade1e6bec072376210c27", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "42360a8c3ce83101fbdf677727b31f20fc4d74a18b7d801fc04d9ffdb5ecc4a9", "generation_seconds_batch": 18.531115247053094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7816922068595886, "target_z": 1.1406249924015521, "ce": 6.340320587158203, "genuineness": 3.7793264389038086, "identity": 0.5690091252326965, "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_Disgust/6e7d18e9b11ed19e9b4f30e8fb99123f45cefd6dd5cade1e6bec072376210c27.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "6ef45f9107527f746312b95da6194075f648e6006891a9ca7e866b2241a48f56", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "affa632eb45210efb138b74ad3809f46a8698e8320550e2e7f0b23616339e2b5", "generation_seconds_batch": 18.928393620066345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01756061613559723, "target_z": -0.4179687367027161, "ce": 6.133810997009277, "genuineness": 4.356721878051758, "identity": 0.6079478859901428, "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_Disgust/6ef45f9107527f746312b95da6194075f648e6006891a9ca7e866b2241a48f56.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "6f53d39af73b64ba8732e5482b8722fa8276ff4cefd9080342388063f5860122", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c42271d600f0ff28002f200067dd5aaef1f455ccda9715f8de8ed9e4a26491b", "generation_seconds_batch": 18.90036421502009, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0035056769847869873, "target_z": -0.46093750379922394, "ce": 6.308549880981445, "genuineness": 4.017816066741943, "identity": 0.6562817096710205, "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_Disgust/6f53d39af73b64ba8732e5482b8722fa8276ff4cefd9080342388063f5860122.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": "6fbde0d4d2bf74174698ace755fb8a2686e6fb1e4734b6ecc1e64d53d55de345", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "21b979ed445ff1d1d700c71e83c87fd4910574a52d28b8fd1d78500816911d31", "generation_seconds_batch": 15.15155573701486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.229520559310913, "target_z": 4.093750106378271, "ce": 5.808161735534668, "genuineness": 3.8546390533447266, "identity": 0.7087708711624146, "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_Disgust/6fbde0d4d2bf74174698ace755fb8a2686e6fb1e4734b6ecc1e64d53d55de345.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "701fb0694208c71f16a1a451898b2297e3cbcfe7efbaca34e484f68e888cc69b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "15da730f0e96cb81f7f3e8ac86e1c24e2f945d4eb843fa19e05d4a7cca782f03", "generation_seconds_batch": 13.660672790952958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5346421599388123, "target_z": 0.6367187822934036, "ce": 6.205295085906982, "genuineness": 3.8295347690582275, "identity": 0.7336814999580383, "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_Disgust/701fb0694208c71f16a1a451898b2297e3cbcfe7efbaca34e484f68e888cc69b.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "709b99f1af184b3f2374fe69bb416722f44b02d3fd7d2a7dafb5fef72ab50afb", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ac026f94dfcb27e4d8a91a78cb2a45bc84c04fe73bf40697d07fca795cad831c", "generation_seconds_batch": 19.32708850700874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10278330743312836, "target_z": -0.24414062405019402, "ce": 6.006728172302246, "genuineness": 4.243753433227539, "identity": 0.5744344592094421, "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_Disgust/709b99f1af184b3f2374fe69bb416722f44b02d3fd7d2a7dafb5fef72ab50afb.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "70bbac9d7abb3706f318d3c860bf3c9bd46f992988f6094eb3ab14c33ebe54f9", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9ad4fdbe1fb1f7b4b8b8da9d1dfaa38ddf9db1d51cd39d2771647f0ac9a9c5c4", "generation_seconds_batch": 18.82117853697855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09608039259910583, "target_z": -0.25781251139767186, "ce": 5.808161735534668, "genuineness": 4.168440818786621, "identity": 0.7309231758117676, "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_Disgust/70bbac9d7abb3706f318d3c860bf3c9bd46f992988f6094eb3ab14c33ebe54f9.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "71211a99fb71097fe3665c80d01dbc14a51f09f6f864ac84858b4f5c45d7e94e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "95be912d211e1cb1153d271843498d1caaf3be8c5bd1ebec98a88c418f03592a", "generation_seconds_batch": 19.921228746999986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08171702921390533, "target_z": -0.28710936075291016, "ce": 6.268836498260498, "genuineness": 3.9676074981689453, "identity": 0.4177584648132324, "hypothesis": "The 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_Disgust/71211a99fb71097fe3665c80d01dbc14a51f09f6f864ac84858b4f5c45d7e94e.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": "71415ee7bedcdcaeaa375ad9d4c3ad8a8e3c90505f04aa5e0de0cc8e2b1c65f8", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5dc283154fbceab03eb94e4ea303be76e05f021a6b88c73c3539b7edea7eeeaa", "generation_seconds_batch": 13.856822889996693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.080450415611267, "target_z": 1.7499999696062083, "ce": 6.205295085906982, "genuineness": 3.798154592514038, "identity": 0.5879272222518921, "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_Disgust/71415ee7bedcdcaeaa375ad9d4c3ad8a8e3c90505f04aa5e0de0cc8e2b1c65f8.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "71d8d63f525e25b9fe33d63f17c92fba78c416e63e4fbc637e9b12854628ea8a", "bucket": "emo_Disgust", "phase": "wording", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "68455c69debf3041c28a91ffeebe8a40cd8d06d4d0e734c0fd17fb65d17a0553", "generation_seconds_batch": 14.098658032948151, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00733591616153717, "target_z": -0.46875001519689585, "ce": 6.141753673553467, "genuineness": 4.582659721374512, "identity": 0.7054518461227417, "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_Disgust/71d8d63f525e25b9fe33d63f17c92fba78c416e63e4fbc637e9b12854628ea8a.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "723f7da15854f44c6bf0e20d798b5ba2af509cee4b521bccfb298951726f4acc", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "b90cfeb2c0793db5393b92a4d76661ee05e043675cb868deae493044c4fa0c45", "generation_seconds_batch": 19.0818137639435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0060699135065078735, "target_z": -0.4414062405019401, "ce": 6.09409761428833, "genuineness": 4.262581825256348, "identity": 0.5557682514190674, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/723f7da15854f44c6bf0e20d798b5ba2af509cee4b521bccfb298951726f4acc.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "7306284e7bad10fdb23099809c7b1ab3a4315d5f9279f57573bd9c97aadfa201", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2e059b78efc1378b80e2a1b0755dd289ac78fca334bb214f5bdf609857a5d64c", "generation_seconds_batch": 19.52521394798532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19087867438793182, "target_z": -0.06445313544786589, "ce": 6.173524379730225, "genuineness": 4.293961524963379, "identity": 0.4658206105232239, "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_Disgust/7306284e7bad10fdb23099809c7b1ab3a4315d5f9279f57573bd9c97aadfa201.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "7338e17cdcdd71d25fdc11890351539aad5abc957d83cd9a4dc4d49f4bed4806", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f3d0ea603e1e89e2f08249a1712530a9e98176e53689020b4cbd783e5d0580b9", "generation_seconds_batch": 18.786491008941084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.028402194380760193, "target_z": -0.511718751899612, "ce": 6.332377910614014, "genuineness": 4.2374773025512695, "identity": 0.4865793287754059, "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_Disgust/7338e17cdcdd71d25fdc11890351539aad5abc957d83cd9a4dc4d49f4bed4806.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "7389472c21169fd2b8c7d224f8c7fb7829d808343f6c050dfa9a176169df3e7c", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ad9556dc2309d77cfa8042cf3be9c13fc1c0e6a4253544d6763df861f5159f06", "generation_seconds_batch": 19.501534519018605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007985025644302368, "target_z": -0.4375, "ce": 6.181467056274414, "genuineness": 4.557555198669434, "identity": 0.4704881012439728, "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_Disgust/7389472c21169fd2b8c7d224f8c7fb7829d808343f6c050dfa9a176169df3e7c.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "73c626f0c2cb8f924986feb6a9542333ed6464f63e67eb5046103c669dfbd4b6", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d386a19cfc66011022599368f43b944d8c86ad03bb6ab342b48b981b3121f4c9", "generation_seconds_batch": 19.528966123005375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012772813439369202, "target_z": -0.42773438354825394, "ce": 6.125868320465088, "genuineness": 4.444586753845215, "identity": 0.8333048224449158, "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_Disgust/73c626f0c2cb8f924986feb6a9542333ed6464f63e67eb5046103c669dfbd4b6.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": "73d698789866626157d7dadd7499e309ae63a4f11114f8e206fda70e469187bc", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "37cf0cc0d974992bf6901e85f49a706433aa01457851502d0b5f5f47b18cbd16", "generation_seconds_batch": 18.54791931307409, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21864786744117737, "target_z": -0.007812511397671884, "ce": 6.0305562019348145, "genuineness": 4.042920112609863, "identity": 0.5171008110046387, "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_Disgust/73d698789866626157d7dadd7499e309ae63a4f11114f8e206fda70e469187bc.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "7407f1f1508c874bc5b7157cd2460287201940e013002378cd5f5658361d9aab", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b8300ec2967c24188a1959cd6fdc4de59cb1d08a01bd37c627f546b08ccf67d9", "generation_seconds_batch": 18.57110298308544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6744456887245178, "target_z": 0.9218750379922396, "ce": 6.09409761428833, "genuineness": 3.8922953605651855, "identity": 0.5115983486175537, "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_Disgust/7407f1f1508c874bc5b7157cd2460287201940e013002378cd5f5658361d9aab.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": "741fd4d6710d7ef24992cd0546cd166aab7b6a46fe8fa9264bd8669b5cc35841", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Escribí el número en el sobre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ebb76374ddb57fbe4b9e6c79e65620be911028e17a3c13100e6b05ae9458d700", "generation_seconds_batch": 13.691169952973723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11906179785728455, "target_z": -0.21093750379922396, "ce": 6.046441555023193, "genuineness": 4.331617832183838, "identity": 0.6693952083587646, "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_Disgust/741fd4d6710d7ef24992cd0546cd166aab7b6a46fe8fa9264bd8669b5cc35841.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "74675bb27a2d864718917ce8d62a83c94c3d5d53a4798c31b2c3a287cc275702", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cab41d888cf318b4b711b59a3ee29ea3e5a7266cdfd4be17704677fb72cf39c5", "generation_seconds_batch": 21.27098125393968, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08171702921390533, "target_z": -0.28710936075291016, "ce": 6.006728172302246, "genuineness": 4.469690799713135, "identity": 0.5048842430114746, "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_Disgust/74675bb27a2d864718917ce8d62a83c94c3d5d53a4798c31b2c3a287cc275702.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "758377ce1d744685478ad9e1ab15dd4cb17ff9738f7546f6640f78fc58cbec1d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5c2881f192033783b905cf49e6cf42e2610be3e9789ee1b165c78792ac722490", "generation_seconds_batch": 18.893311197985895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09895307570695877, "target_z": -0.25195312025097005, "ce": 6.23706579208374, "genuineness": 4.394378662109375, "identity": 0.8202953934669495, "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_Disgust/758377ce1d744685478ad9e1ab15dd4cb17ff9738f7546f6640f78fc58cbec1d.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "75a700f1dadd613a4003c4596f3f57bb1c368798e1ed2921110282187034a33a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2f89285cb4e056b94dba206004352458ebdabfbdf3a76c8f57bb7126da628bec", "generation_seconds_batch": 20.893441542051733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055862948298454285, "target_z": -0.33984374430116404, "ce": 6.2767791748046875, "genuineness": 4.425758361816406, "identity": 0.46937450766563416, "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_Disgust/75a700f1dadd613a4003c4596f3f57bb1c368798e1ed2921110282187034a33a.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": "75fca95c78ab5500989c7954bebad7f12ee7de92243b95209d2813ba02b0fdb1", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The road turns left behind the bridge.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b9688ba9d65aabdbe5e7340c6f9bae5468aebbc3eee5ea885bdf17d98375a41c", "generation_seconds_batch": 13.61094427399803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4925096035003662, "target_z": 0.5507813088879714, "ce": 6.229123115539551, "genuineness": 3.6287014484405518, "identity": 0.3673470616340637, "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_Disgust/75fca95c78ab5500989c7954bebad7f12ee7de92243b95209d2813ba02b0fdb1.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "76130958e299f34de126079de3d8148a9a7adbd3e4dd452db3c639495ca21b96", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "f80746de73a3cf5845db307fd186a204d0125d76af60b59067f82f2705385dea", "generation_seconds_batch": 13.820246979012154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2808891534805298, "target_z": 0.11914059365640232, "ce": 5.998785495758057, "genuineness": 3.9801597595214844, "identity": 0.7314453125, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/76130958e299f34de126079de3d8148a9a7adbd3e4dd452db3c639495ca21b96.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "762eafc50f9bca1298417be379738bb08cc6316630c35a569924388539e9d2e4", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c0245e55963fc05c63444832a0a3199384a558c65ff5de53808765b8b0c97ac", "generation_seconds_batch": 22.226157338009216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5633689165115356, "target_z": 0.6953125417914636, "ce": 6.181467056274414, "genuineness": 4.1998209953308105, "identity": 0.3635024428367615, "hypothesis": "Die Tür 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_Disgust/762eafc50f9bca1298417be379738bb08cc6316630c35a569924388539e9d2e4.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": "769358aa19c5808325bf7f9154a998d034ab99f2e297bc0cf0e9d44742590743", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Someone moved the little blue chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4f9da5f37a33ed79b2bbd6acfedaa28bb1b21548289eaf8bb40c8ab593fb9cdb", "generation_seconds_batch": 18.843967269989662, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04437224566936493, "target_z": -0.36328124810038803, "ce": 6.173524379730225, "genuineness": 3.553389072418213, "identity": 0.2971057891845703, "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_Disgust/769358aa19c5808325bf7f9154a998d034ab99f2e297bc0cf0e9d44742590743.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "76fc41f9da00ec7582236a60893981fbccd9f0462f026d04a097316878aac613", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "8c4fe03c754ed5017293187cd360fb7ffed51625e4bfc6f7f61dad52c5d68a54", "generation_seconds_batch": 16.35766903392505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05107516050338745, "target_z": -0.34960936075291016, "ce": 6.157639026641846, "genuineness": 4.20609712600708, "identity": 0.457210510969162, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/76fc41f9da00ec7582236a60893981fbccd9f0462f026d04a097316878aac613.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "773586ff44a31fa3dd48ba3bcc1516a648168bab63395822ccfb97b7e512de4e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d0879db487c8fe4270fde9bacb05d12872d2b710b643f2edb6623c2b8b7a9d02", "generation_seconds_batch": 14.20583973499015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.013081252574920654, "target_z": -0.4804687367027161, "ce": 6.332377910614014, "genuineness": 4.218649387359619, "identity": 0.6677157878875732, "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_Disgust/773586ff44a31fa3dd48ba3bcc1516a648168bab63395822ccfb97b7e512de4e.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "778a1669521639c5d38f0e6eabefe66ff66d4abc0ad1bb983066a26f070a2bcd", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "002c4abee3de528109e405a57de42b2872dd8ca3079d65f844a581340683f7d4", "generation_seconds_batch": 13.807074547978118, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1056559830904007, "target_z": -0.23828124810038803, "ce": 6.09409761428833, "genuineness": 4.218649387359619, "identity": 0.4154098331928253, "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_Disgust/778a1669521639c5d38f0e6eabefe66ff66d4abc0ad1bb983066a26f070a2bcd.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "4a7911cfd03d767f2ecdc8c3f6d72d9881db4fe58ce41d2a19c6f118e3c44b83", "generation_seconds_batch": 13.635752356029116, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.059693172574043274, "target_z": -0.3320312632972839, "ce": 6.157639026641846, "genuineness": 4.532451152801514, "identity": 0.8080084323883057, "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_Disgust/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "77d394c6d6baf359de2ce4d1addbed40e7b68807251587a98e121d967214ee03", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "843b3de983392e23b1ed98564832d7e53f11ec064284f630071297c10ff47712", "generation_seconds_batch": 19.637052224949002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1099649965763092, "target_z": -0.22949218417567904, "ce": 6.125868320465088, "genuineness": 4.770940780639648, "identity": 0.48557841777801514, "hypothesis": "Die Tür 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_Disgust/77d394c6d6baf359de2ce4d1addbed40e7b68807251587a98e121d967214ee03.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "77e0422369d4c4f44ff4856949d2ff185f397e1885195c055548031f344cd5f6", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bf307ace431bf4bdc80acf25f5d1175f2efe61dfe03cf92765c78b1c4866ebc9", "generation_seconds_batch": 13.64456719905138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09608039259910583, "target_z": -0.25781251139767186, "ce": 5.879645347595215, "genuineness": 4.231201171875, "identity": 0.4717882573604584, "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_Disgust/77e0422369d4c4f44ff4856949d2ff185f397e1885195c055548031f344cd5f6.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": "78119e67b05961593368a1768735dcf05c7d95dd973e46547182edade3bc712a", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fa21beeff0a331a71f491519c53646bf0b443bc8b071321ad72d90397e3173fe", "generation_seconds_batch": 16.290304147987626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.040542006492614746, "target_z": -0.3710937594980599, "ce": 6.086154937744141, "genuineness": 4.13078498840332, "identity": 0.7431114912033081, "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_Disgust/78119e67b05961593368a1768735dcf05c7d95dd973e46547182edade3bc712a.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "782a333d50a64c817323b539f5fa2aeb8d8beedfeecd2a3b264838d5ecebee57", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4c872a1dc553e778971c56f446bbdae78bf4126d11b04d0562d30eeb1b48a684", "generation_seconds_batch": 21.099842629977502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08171702921390533, "target_z": -0.28710936075291016, "ce": 6.284721851348877, "genuineness": 4.444586753845215, "identity": 0.5897998809814453, "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_Disgust/782a333d50a64c817323b539f5fa2aeb8d8beedfeecd2a3b264838d5ecebee57.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "7836ec0f9d7f499e680304b90afdc10b20a67eee171274582a650e00a5e91946", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d712eda94768497093fa7ba6a33459a6de66ff57af1b71d4ae394219587eeb86", "generation_seconds_batch": 15.931227068067528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10086818784475327, "target_z": -0.24804687974902995, "ce": 6.109982967376709, "genuineness": 4.331617832183838, "identity": 0.5136856436729431, "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_Disgust/7836ec0f9d7f499e680304b90afdc10b20a67eee171274582a650e00a5e91946.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "787afbbaa2e372bb8f80117e9fb66827f47f0ccbbbef8a7864151c5e8bc3af85", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1de1fe1a3d95f14f8cfbf9c567f72a7363262c2b05f528d36f430317e6a52051", "generation_seconds_batch": 20.0280799070606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02169927954673767, "target_z": -0.4980468645521341, "ce": 6.205295085906982, "genuineness": 4.6956281661987305, "identity": 0.6206070184707642, "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_Disgust/787afbbaa2e372bb8f80117e9fb66827f47f0ccbbbef8a7864151c5e8bc3af85.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "789100c49a836e4dbb6f066a6171ca203333880d1451a0821e50871897c1fbca", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "845542a67de10718b6b33c194e24beb8d58b4b2d48a6541eb2d90b8e01aeb293", "generation_seconds_batch": 18.932744282996282, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005112349987030029, "target_z": -0.443359375949806, "ce": 6.125868320465088, "genuineness": 4.65797233581543, "identity": 0.8684321641921997, "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_Disgust/789100c49a836e4dbb6f066a6171ca203333880d1451a0821e50871897c1fbca.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "78963cf4e62814ae23be5ef64d9c8d9b5da7d11aa8c12438faae056a9e59e18f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ccdcd85e07b1db2e01cc1e9d780598163c51c0c039963028c3f7990e0a4f371f", "generation_seconds_batch": 18.585920298937708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11140133440494537, "target_z": -0.22656249620077604, "ce": 6.117925643920898, "genuineness": 3.873466968536377, "identity": 0.7278503775596619, "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_Disgust/78963cf4e62814ae23be5ef64d9c8d9b5da7d11aa8c12438faae056a9e59e18f.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "78b6271f8115e2ff74af27a48abbe2798258b91e313b370fb566e5433d75f217", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3da1b8ef2d8822d9acf0cc7e69b62d6402278a9bd457376fa06c83e3f4435460", "generation_seconds_batch": 20.28178406599909, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13821296393871307, "target_z": -0.17187500759844793, "ce": 6.229123115539551, "genuineness": 4.532451152801514, "identity": 0.5773394107818604, "hypothesis": "Die Tür 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_Disgust/78b6271f8115e2ff74af27a48abbe2798258b91e313b370fb566e5433d75f217.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "beb658a0e326ed1bc9f7863a669556ab6187e5611f7d1a9d04777d93a2df0e83", "generation_seconds_batch": 13.811165546067059, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03766933083534241, "target_z": -0.3769531354478659, "ce": 6.2767791748046875, "genuineness": 4.519899368286133, "identity": 0.6487674713134766, "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_Disgust/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "79cd771caebedd82562ac9b32e9a71156726434610357a890df9f1a79bffa3b7", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "00f4c81702491121a393b0b3914dbb8dd6c178d4b5e9a01b4fbbae2440de9330", "generation_seconds_batch": 18.81578950607218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.040542006492614746, "target_z": -0.3710937594980599, "ce": 6.173524379730225, "genuineness": 4.20609712600708, "identity": 0.5764869451522827, "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_Disgust/79cd771caebedd82562ac9b32e9a71156726434610357a890df9f1a79bffa3b7.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "7a0e255d2d0867e8f53bf8c1816e2480ab3a08afdc5168ddd6d728e90b943aa1", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6b6e911c7a84a4f36bd992477b16560b63b3883098df14b5a93750907567ffb1", "generation_seconds_batch": 18.89746289595496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1985391527414322, "target_z": -0.048828112652522127, "ce": 6.252951145172119, "genuineness": 4.137060642242432, "identity": 0.5481330156326294, "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_Disgust/7a0e255d2d0867e8f53bf8c1816e2480ab3a08afdc5168ddd6d728e90b943aa1.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "7acd42d3f4f1a70506bf657ad45d792af7dafdd0ab963189e171941433e92a29", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b0f2d461f5176bb25a1970cc65bf86c8d4f7f80f4e0197804920b9dab6bac9fc", "generation_seconds_batch": 18.781612343969755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06256584823131561, "target_z": -0.3261718873474779, "ce": 6.038498878479004, "genuineness": 3.9801597595214844, "identity": 0.6262456178665161, "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_Disgust/7acd42d3f4f1a70506bf657ad45d792af7dafdd0ab963189e171941433e92a29.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": "7b569f589815798e976cc47b0a26037c4ddd79f8415df2fd9467a61b642bb39f", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2e460d5c19c045282cb11c07b44adf1b302356529c0d9f54634ad18ec10ad6fc", "generation_seconds_batch": 13.74069068301469, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07405655086040497, "target_z": -0.30273438354825394, "ce": 5.879645347595215, "genuineness": 3.8922953605651855, "identity": 0.4329339861869812, "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_Disgust/7b569f589815798e976cc47b0a26037c4ddd79f8415df2fd9467a61b642bb39f.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "7b93dc6d50ac3e72adb9328955a41d2493a7218ed53c92b48897989945d898e5", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "73bcbc8810da7eb0aaf4e8b7e6649a14a5804a987f057f540a5310fd7a7fabfd", "generation_seconds_batch": 19.31778772198595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12289203703403473, "target_z": -0.20312499240155207, "ce": 6.125868320465088, "genuineness": 4.457139015197754, "identity": 0.759054958820343, "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_Disgust/7b93dc6d50ac3e72adb9328955a41d2493a7218ed53c92b48897989945d898e5.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "7bf728d1fca71e74836ce50d02095378180a4b0683dc0f5b415957234e32e1ca", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3e68b56a9fc1e47fb19bb81e31f2281b497b40d765cc246d5fad088a870fc50a", "generation_seconds_batch": 18.745470514986664, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.129934310913086, "target_z": 3.8906247492512187, "ce": 6.252951145172119, "genuineness": 3.8169827461242676, "identity": 0.5243014097213745, "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_Disgust/7bf728d1fca71e74836ce50d02095378180a4b0683dc0f5b415957234e32e1ca.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "7c18eef8f70fbec527139bbcd72301387ff82b32f7d5dad0d0777d879386ba58", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "973afda83a6fc76e99be9efd9e7c66c36aa110552cc00e0d1ef8474a026ea151", "generation_seconds_batch": 18.77635520894546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06543852388858795, "target_z": -0.32031251139767186, "ce": 6.038498878479004, "genuineness": 4.375550270080566, "identity": 0.536199152469635, "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_Disgust/7c18eef8f70fbec527139bbcd72301387ff82b32f7d5dad0d0777d879386ba58.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "7c30fd373332b9d99f3e6ad9a6319e47be80036a31a9bec2da6dec6204f78771", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "60872ef506c00922a059b6c52ffa676154f91ce32cf1e6e16619c7670e2ae898", "generation_seconds_batch": 13.798201110912487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2796226739883423, "target_z": 2.156250197559646, "ce": 6.078212261199951, "genuineness": 3.961331605911255, "identity": 0.7741512060165405, "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_Disgust/7c30fd373332b9d99f3e6ad9a6319e47be80036a31a9bec2da6dec6204f78771.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "7c790d8695d28ed8b4290c9ceca54252df8ba50caf34a544eab6fd021aa2be7a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "41881732933f6645b5f774d2e6de8fac71c4967aa93d147b7546e638a731baee", "generation_seconds_batch": 18.788648099056445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1286373734474182, "target_z": -0.19140627089573178, "ce": 6.197352409362793, "genuineness": 4.243753433227539, "identity": 0.6021894216537476, "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_Disgust/7c790d8695d28ed8b4290c9ceca54252df8ba50caf34a544eab6fd021aa2be7a.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "7d76446d818a6d7bd1c29835a98051f83f3b6c2b5070c8e51700a105c5130728", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "da58174764b3ff5fe9aff01c59a126506b7a29246754acf05687254cefa2d31a", "generation_seconds_batch": 18.968429408967495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.053298696875572205, "target_z": -0.5624999696062083, "ce": 6.419747352600098, "genuineness": 4.243753433227539, "identity": 0.4537202715873718, "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_Disgust/7d76446d818a6d7bd1c29835a98051f83f3b6c2b5070c8e51700a105c5130728.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "7dd97ce74a7fc30ee8c3b672cda0029a0dfe0cbfaa4856b679817bc877a9bb82", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cfc8271380daee7ca85116d29f713c36da4f252481a784ae03fcd357ecb2ce48", "generation_seconds_batch": 19.01552396803163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11044377088546753, "target_z": -0.22851563164864194, "ce": 6.157639026641846, "genuineness": 3.8044304847717285, "identity": 0.4376646876335144, "hypothesis": "The 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_Disgust/7dd97ce74a7fc30ee8c3b672cda0029a0dfe0cbfaa4856b679817bc877a9bb82.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "7eeef7979acd1dec12b0c1e7212023c1d07afc0bc35be60b39e8476b59f30562", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fac2437aadda1c38436abd80d0d9a18f47f701e12a539c2c5e40ac6b2f91cd22", "generation_seconds_batch": 18.8949988669483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022348403930664062, "target_z": -0.40820312025097005, "ce": 6.38003396987915, "genuineness": 4.086852550506592, "identity": 0.6838634610176086, "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_Disgust/7eeef7979acd1dec12b0c1e7212023c1d07afc0bc35be60b39e8476b59f30562.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "7efb58034cbcf2b75d5adda7c7a92a6c571e191b12cc73fbb0c0ffb464154957", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4141434aef0a573114842d4b8c5c2dbd851039d49fc4bf24cdc71074122f7c51", "generation_seconds_batch": 18.919664756977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05107516050338745, "target_z": -0.34960936075291016, "ce": 6.2767791748046875, "genuineness": 4.457139015197754, "identity": 0.739105224609375, "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_Disgust/7efb58034cbcf2b75d5adda7c7a92a6c571e191b12cc73fbb0c0ffb464154957.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "7f36fceb0560dfa1480fc639fee1deb12f7532361fe94b86a8c8dfa580348cc9", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6c138173dfbbaa46a2c54d02c1c3161d3bc75f43db5a63af6cdde0ccb5533162", "generation_seconds_batch": 18.58571719797328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3014766573905945, "target_z": 0.16113277783208135, "ce": 6.252951145172119, "genuineness": 4.293961524963379, "identity": 0.6620339155197144, "hypothesis": "Die Tür 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_Disgust/7f36fceb0560dfa1480fc639fee1deb12f7532361fe94b86a8c8dfa580348cc9.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "7f4d48ad83f05ae3b4a02e849c48ca9aead3a80aaa9377fc9c49bca5c272738a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "16fb4c83ae84754ce0ac75f6a500160e7273cdc88dcf6d18f1b7e135e592e02e", "generation_seconds_batch": 18.804265890968964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08363214135169983, "target_z": -0.28320312025097005, "ce": 5.77639102935791, "genuineness": 3.923675537109375, "identity": 0.43759191036224365, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschappen.", "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_Disgust/7f4d48ad83f05ae3b4a02e849c48ca9aead3a80aaa9377fc9c49bca5c272738a.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "7f590ff3d6b656324ae359e5ae60369c6de7c859a02c76afd16b68d34e88ae22", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a06fd37ab80c8be29b3a4431f89cda2a6dbf0893db9c2bd9b007894bd0bb5f19", "generation_seconds_batch": 20.39458282000851, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03797776997089386, "target_z": -0.5312499848031041, "ce": 6.09409761428833, "genuineness": 4.595211505889893, "identity": 0.6962672472000122, "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_Disgust/7f590ff3d6b656324ae359e5ae60369c6de7c859a02c76afd16b68d34e88ae22.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "1d8eb715101a82a64d877aea6e8a2bc26f0df406bae803eecbd958b3a8df0cc4", "generation_seconds_batch": 15.037744753062725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020433291792869568, "target_z": -0.41210936075291016, "ce": 6.332377910614014, "genuineness": 4.444586753845215, "identity": 0.33313387632369995, "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_Disgust/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "7f972be4f433abe9542503e5f0651af7ed5f545f9482198ebf00f6c6c0516e97", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "987007b7a1f6175eef061cb90b059ff6362bd21253c4531b404e30ce75a869e2", "generation_seconds_batch": 19.030609612935223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12001936137676239, "target_z": -0.20898436835135806, "ce": 6.181467056274414, "genuineness": 4.118232727050781, "identity": 0.6869158744812012, "hypothesis": "De de deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/7f972be4f433abe9542503e5f0651af7ed5f545f9482198ebf00f6c6c0516e97.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": "7fc001e411d02cf2ae30d9e02b25a784d1fd752cc3f1ccd1ec019b7c94c78417", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "935b66b1f1ea3ee49f68f92539e43f669d1ea38af6a76bf288aa3a48ac38ee5a", "generation_seconds_batch": 13.613788124057464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17076995968818665, "target_z": -0.10546873670271613, "ce": 6.173524379730225, "genuineness": 3.8044304847717285, "identity": 0.6681580543518066, "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_Disgust/7fc001e411d02cf2ae30d9e02b25a784d1fd752cc3f1ccd1ec019b7c94c78417.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "8090e917eb5193fae4df82df3b8d6a3860acb52208e80437ac960516f74ecea6", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f9ea74337b0fa40b0dd00af9693589a9b59fec6824c88cb4706ea5adcb83e00c", "generation_seconds_batch": 18.48711035505403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.122583031654358, "target_z": 1.8359375645868072, "ce": 5.9431867599487305, "genuineness": 3.8169827461242676, "identity": 0.7067756652832031, "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_Disgust/8090e917eb5193fae4df82df3b8d6a3860acb52208e80437ac960516f74ecea6.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "81f4b270886bef175fbf1f337a7f31b538a092137b470d7e65935f6c200b1952", "generation_seconds_batch": 13.679154508048669, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01564548909664154, "target_z": -0.4218750075984479, "ce": 6.3641486167907715, "genuineness": 4.218649387359619, "identity": 0.6311941146850586, "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_Disgust/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "80d03c819e0159e6d6dd5d2a385d839db3b14834e5add839823ca9abd0934cac", "bucket": "emo_Disgust", "phase": "wording", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d77872ec37871d58caabbe138fbdafdf1b2044773bc49923503107f76e85c45d", "generation_seconds_batch": 14.196581730036996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0820254534482956, "target_z": -0.6210937291042682, "ce": 6.3641486167907715, "genuineness": 4.545003414154053, "identity": 0.4874051809310913, "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_Disgust/80d03c819e0159e6d6dd5d2a385d839db3b14834e5add839823ca9abd0934cac.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "80dcc2632cd3c2c07fa1133a520d867fae35a550e83b7193aac70c5b4075820c", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "47f86e725f6bef29718949448c9dcdea18da2e07445efd6cdbf9628c82e62d8f", "generation_seconds_batch": 19.015996044967324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.06861965358257294, "target_z": -0.5937500151968959, "ce": 6.165581703186035, "genuineness": 3.9801597595214844, "identity": 0.4173256754875183, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/80dcc2632cd3c2c07fa1133a520d867fae35a550e83b7193aac70c5b4075820c.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "8108507a88f48181d8fec17d8e4c6ee430ee5472c56e4728cc99bfbc76acc145", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5abc6c48e0306ec14782f2288e261c267317c5121bbeb662228285d8afeda1a1", "generation_seconds_batch": 18.837509626057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.040542006492614746, "target_z": -0.3710937594980599, "ce": 6.157639026641846, "genuineness": 4.256305694580078, "identity": 0.6609171032905579, "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_Disgust/8108507a88f48181d8fec17d8e4c6ee430ee5472c56e4728cc99bfbc76acc145.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "819b7798c40e268fd2dba40f35701ebf703c05364001f04f91fa6d8d78f87b3d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "59e58f6751d49ca884610f6a7250a95865c781dc24e830a85e2790b901e2a26c", "generation_seconds_batch": 20.28801999206189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06543852388858795, "target_z": -0.32031251139767186, "ce": 6.300607204437256, "genuineness": 3.8797430992126465, "identity": 0.27742958068847656, "hypothesis": "The 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_Disgust/819b7798c40e268fd2dba40f35701ebf703c05364001f04f91fa6d8d78f87b3d.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": "822f6eebe7395136b9eb18855e3a44c83bb33e6c428c36fefa3ed984d1a4f901", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "74201d068ce0b862ed675cf0c3729b6eba0720d55d92eb67c3c0cac6794109a1", "generation_seconds_batch": 18.617334779002704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.290804386138916, "target_z": 4.218750288741021, "ce": 5.927301406860352, "genuineness": 3.4121780395507812, "identity": 0.6661489009857178, "hypothesis": "Telkin had placed the petite chaise blue. Elle is ici, pretty launch bibliothek. We remettruns after the dejection.", "wer": 0.8095238095238095, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/822f6eebe7395136b9eb18855e3a44c83bb33e6c428c36fefa3ed984d1a4f901.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "8355fd1fd0cbdda772529f3a5de24662e711e378d96a4ff0a8bd5f30e706c6a9", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a537970c7f4e69b35a33a30dd1b6b0568b0d7ebaf3d092cf6db4459f2a7eaff2", "generation_seconds_batch": 21.998380220960826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01564548909664154, "target_z": -0.4218750075984479, "ce": 5.95112943649292, "genuineness": 3.9676074981689453, "identity": 0.5782641172409058, "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_Disgust/8355fd1fd0cbdda772529f3a5de24662e711e378d96a4ff0a8bd5f30e706c6a9.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "8406920478a39abc39954fd0e4f2787b4873ab88afbecd61604f400d7fe82f30", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b4e5e9dfccbf9ddca2bd7a8001d1ce731a3e9257a0e0f486bf36b41bc608f4b4", "generation_seconds_batch": 21.681823451071978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17076995968818665, "target_z": -0.10546873670271613, "ce": 6.284721851348877, "genuineness": 4.250029563903809, "identity": 0.6815263032913208, "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_Disgust/8406920478a39abc39954fd0e4f2787b4873ab88afbecd61604f400d7fe82f30.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "84868c4d5be41679658d3824a5a90c5ba9bdf2b62677005fd0289bcff7b675e8", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "988c9d8980c943b48ad4b765c60e6b0ed8ec8b083edd8f022855798427eeb7da", "generation_seconds_batch": 20.67384302301798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07118387520313263, "target_z": -0.3085937594980599, "ce": 6.38797664642334, "genuineness": 4.6705241203308105, "identity": 0.5370727181434631, "hypothesis": "Die Tür 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_Disgust/84868c4d5be41679658d3824a5a90c5ba9bdf2b62677005fd0289bcff7b675e8.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "84c93477fa5bd94b1205eae057108918c48df5156da6b5e076c5f48f9c04ef45", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "afd2201708ff6a1bd6314034754cca02996f51683b7e5e8745c7b9cb46d1a27f", "generation_seconds_batch": 18.69804521801416, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06926876306533813, "target_z": -0.3125, "ce": 6.0305562019348145, "genuineness": 3.9801597595214844, "identity": 0.3508908748626709, "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_Disgust/84c93477fa5bd94b1205eae057108918c48df5156da6b5e076c5f48f9c04ef45.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "8502a80207d01edc8589ec14bfb9cc5820459ff6fad147069327a3ca2334d9cd", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "83e1c3c9d9748c5abe519b91aeae65c536810011819f44ae7c9164c07b89f045", "generation_seconds_batch": 22.18224699201528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.053298696875572205, "target_z": -0.5624999696062083, "ce": 6.435632705688477, "genuineness": 4.413206577301025, "identity": 0.4046728014945984, "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_Disgust/8502a80207d01edc8589ec14bfb9cc5820459ff6fad147069327a3ca2334d9cd.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": "8531c1f3497ee9dc84a6f5f62f397ca94483ab6064fb5930b1634f1ba5035a37", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Your message arrived after I had left.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "45fffa1d289da6590cebdb19cac4c480d82593083aafd42bee201d6672c1bff4", "generation_seconds_batch": 18.888650448061526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2933374345302582, "target_z": 0.14453126329728386, "ce": 6.181467056274414, "genuineness": 3.7542223930358887, "identity": 0.6251600384712219, "hypothesis": "Your message arrived after I had left. I've read it twice, before putting the phone away. Let me know when we can talk.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/8531c1f3497ee9dc84a6f5f62f397ca94483ab6064fb5930b1634f1ba5035a37.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "853398301a279f1c0b827a62affe62c45b139340981a0345a887e2e0846dcc76", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8fe09542e6fd8f0484062a30794afd195aab01e84d9ef48f3e9c46666cb0cc27", "generation_seconds_batch": 13.754100963007659, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07501411437988281, "target_z": -0.30078124810038803, "ce": 5.998785495758057, "genuineness": 4.325342178344727, "identity": 0.6976420879364014, "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_Disgust/853398301a279f1c0b827a62affe62c45b139340981a0345a887e2e0846dcc76.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "8541cf8922f9113a6e7d249bcc3a223fbb874d1d3cee1279b706042b73dbcf6b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "073d09f3ab85a879583bb3d28899214fca03726ef9cb5293c97ce17c23c60bdb", "generation_seconds_batch": 18.863160587963648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.723929762840271, "target_z": 3.0625001823627502, "ce": 6.284721851348877, "genuineness": 3.7793264389038086, "identity": 0.6312732696533203, "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_Disgust/8541cf8922f9113a6e7d249bcc3a223fbb874d1d3cee1279b706042b73dbcf6b.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": "85a8f745e55fb9de4da1c4b2af275905a563059abb4fe54fbc2e1237ba8a2895", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The keys are on the kitchen table.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "35a9d5b4bbaf5621ac6194620f765709d02044a378455620f640bcd12f644f9c", "generation_seconds_batch": 18.67156518192496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1698123961687088, "target_z": -0.10742187215058203, "ce": 5.903473377227783, "genuineness": 3.616149425506592, "identity": 0.38727015256881714, "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_Disgust/85a8f745e55fb9de4da1c4b2af275905a563059abb4fe54fbc2e1237ba8a2895.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": "86264ad2b6dcf73d317a6fbb44913264ce6257991ff4920a618e213e8fb1d160", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The keys are on the kitchen table.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bbf2ca19209e98ae7096fccbbb2ce9a00ae3e45c7ba9d1cfb8a98c929e19c64a", "generation_seconds_batch": 13.698188609094359, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1037408635020256, "target_z": -0.24218750379922396, "ce": 6.09409761428833, "genuineness": 3.418454170227051, "identity": 0.36809468269348145, "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_Disgust/86264ad2b6dcf73d317a6fbb44913264ce6257991ff4920a618e213e8fb1d160.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "8683cc3086add7d8a3b2a809bdeb63f6b9e6d35bea34c14d5547e5960183899e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2b4ae1ab428a743a9e72eafb5c76129e75cb1fac09dc590a22eb60d6499bb4a4", "generation_seconds_batch": 18.962981618009508, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09033504128456116, "target_z": -0.2695312632972839, "ce": 6.173524379730225, "genuineness": 4.243753433227539, "identity": 0.5237430930137634, "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_Disgust/8683cc3086add7d8a3b2a809bdeb63f6b9e6d35bea34c14d5547e5960183899e.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "868434cbac052e536ca670a0eaa622232c9420d672f5a55cde99f1cf68bbc4c2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "755f73740d112b88529993305e3a45a9be3a3fb74d83200fdcc26b09469f00e0", "generation_seconds_batch": 19.01552396803163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09991063177585602, "target_z": -0.25, "ce": 6.149696350097656, "genuineness": 3.898571252822876, "identity": 0.3987792730331421, "hypothesis": "The 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_Disgust/868434cbac052e536ca670a0eaa622232c9420d672f5a55cde99f1cf68bbc4c2.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "87601eb5f9f1f3eca6e0051ec36e3edca1823fb1f78b29b1b548c4a5e0a53e41", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "19741389498e682d81040e1676def67edd8d370cd74d7831d9714db512980ac8", "generation_seconds_batch": 18.77927955100313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5710293650627136, "target_z": 0.7109375037992239, "ce": 5.982900142669678, "genuineness": 4.13078498840332, "identity": 0.48665910959243774, "hypothesis": "Die Tür 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_Disgust/87601eb5f9f1f3eca6e0051ec36e3edca1823fb1f78b29b1b548c4a5e0a53e41.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "876759827c9b7363597b5d68cc213711f9ffc9bc24b2c1a30384c46fa6660331", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b506e7da6e395830b607f22ddd897c9ba364b2a8cacacc764c7b95976c2e9337", "generation_seconds_batch": 14.689833348034881, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19087867438793182, "target_z": -0.06445313544786589, "ce": 6.2767791748046875, "genuineness": 4.21237325668335, "identity": 0.7285113334655762, "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_Disgust/876759827c9b7363597b5d68cc213711f9ffc9bc24b2c1a30384c46fa6660331.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "8782a36f601ed7af897976515efa8fb79aaf3f3f4a37b690f743a2812b5235ea", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1bbf2fc4f8c5233ae0a3cb194693f3eeaad34ee7f082d91f651c5a3ab7df66b4", "generation_seconds_batch": 18.869263818953186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.049468472599983215, "target_z": -0.5546874886023281, "ce": 6.475345611572266, "genuineness": 4.6203155517578125, "identity": 0.665747880935669, "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_Disgust/8782a36f601ed7af897976515efa8fb79aaf3f3f4a37b690f743a2812b5235ea.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "87da61ad034e5ae151acd70c67cf99d9359b9dda2e8cf3f92f7c8b6679f47513", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a5972f631b807f47c86c1233957dc69c5cac18a1b26bcb223804ca1b5d40de5b", "generation_seconds_batch": 18.955616458086297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10757109522819519, "target_z": -0.23437500759844793, "ce": 6.006728172302246, "genuineness": 4.457139015197754, "identity": 0.7717776298522949, "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_Disgust/87da61ad034e5ae151acd70c67cf99d9359b9dda2e8cf3f92f7c8b6679f47513.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "885a2376c662cc0f629795825091cdbddc5377430050598caa7206424debcc20", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "244a6397ef19a6ecbfcba5e81ea451561046f00416c49beaf19061794b2e0e54", "generation_seconds_batch": 18.591923584928736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27418625354766846, "target_z": 0.10546873670271613, "ce": 6.229123115539551, "genuineness": 3.6412534713745117, "identity": 0.3122851848602295, "hypothesis": "The 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_Disgust/885a2376c662cc0f629795825091cdbddc5377430050598caa7206424debcc20.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "887bf25bc0639ca7f94197958ede56b7b09ffa05be9d54d5d0fa38b757766ea0", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "acbbbc64924063b19fbf026ecb2af2f79d3986a25294f213014a91fce39f5c61", "generation_seconds_batch": 20.186467583989725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0003245621919631958, "target_z": -0.4531249924015521, "ce": 6.292664527893066, "genuineness": 4.532451152801514, "identity": 0.7955743074417114, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/887bf25bc0639ca7f94197958ede56b7b09ffa05be9d54d5d0fa38b757766ea0.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "8882ad34e4a1d48aed7e53b88122d5059022b8bde912532d562b47cb677f53ec", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c95a81eea9015469246be9e2929b3657b332152916a604d68698133519ed6eda", "generation_seconds_batch": 18.937570973997936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5097455978393555, "target_z": 0.5859374430116405, "ce": 6.197352409362793, "genuineness": 4.394378662109375, "identity": 0.6313327550888062, "hypothesis": "Die Tür 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_Disgust/8882ad34e4a1d48aed7e53b88122d5059022b8bde912532d562b47cb677f53ec.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "888b4b5d769957da569499c54474feb2827a8e2c2482d616656badb94f0503fb", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ed58ab96467e3b76c0d542774361d2e0e6ea35f6c9dd6245e9d1bd0053eff107", "generation_seconds_batch": 18.6227251640521, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16598215699195862, "target_z": -0.11523438354825391, "ce": 6.109982967376709, "genuineness": 3.5063188076019287, "identity": 0.33512020111083984, "hypothesis": "The 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_Disgust/888b4b5d769957da569499c54474feb2827a8e2c2482d616656badb94f0503fb.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "88a85cd1c898a7b96bf2085aceeb1d682eea2f56e75c835bf093ec5585e1dafc", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "851e2776903520338084a5fce4bfda95a10b1a18ea70d99e9f8311bcadbcfa93", "generation_seconds_batch": 19.610767800942995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02905130386352539, "target_z": -0.3945312632972839, "ce": 6.141753673553467, "genuineness": 4.425758361816406, "identity": 0.580535888671875, "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_Disgust/88a85cd1c898a7b96bf2085aceeb1d682eea2f56e75c835bf093ec5585e1dafc.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "88e2f62ba18db8adee3dbfba8e8fe15a6f4e03ba9c6b857db0186adbebfebbd1", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "82afc936c35f82acabb6bb081f6d783b4a01b53444cc6e9a514326d0bab14434", "generation_seconds_batch": 13.688958378974348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05712895095348358, "target_z": -0.5703125113976719, "ce": 6.221180438995361, "genuineness": 4.419482707977295, "identity": 0.517238438129425, "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_Disgust/88e2f62ba18db8adee3dbfba8e8fe15a6f4e03ba9c6b857db0186adbebfebbd1.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "89c3ea3642977d6f0ccd63e8b90f859fb17d8d991a31790c2b8b458c40ff8150", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f925331d3a60d8b664174d945936cdd6f5b4485a91f37eede233a2027fb7c1f2", "generation_seconds_batch": 18.722265279036947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10757109522819519, "target_z": -0.23437500759844793, "ce": 6.229123115539551, "genuineness": 4.582659721374512, "identity": 0.41402456164360046, "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_Disgust/89c3ea3642977d6f0ccd63e8b90f859fb17d8d991a31790c2b8b458c40ff8150.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "89cc26969b7b6d9b1562d304ef5a80368a24d3d5f58f9c0247961c447e171a18", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "665b71c2e524ce5bbcefd34e844f0d13309374dbc7cab8edb53ab34ac3694549", "generation_seconds_batch": 22.378481727093458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.026487082242965698, "target_z": -0.5078125113976719, "ce": 6.1894097328186035, "genuineness": 4.375550270080566, "identity": 0.5395417213439941, "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_Disgust/89cc26969b7b6d9b1562d304ef5a80368a24d3d5f58f9c0247961c447e171a18.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": "8a1873d9d72ecfafc513af415987204d057c97729295393d3137a51b3e66fb13", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "dbb68155a46394ce4d6e911b4bb7814cbe58153f5a1641a145281b0075402afc", "generation_seconds_batch": 19.034079334931448, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5365572571754456, "target_z": 0.6406249924015521, "ce": 5.414999485015869, "genuineness": 3.6663577556610107, "identity": 0.475921094417572, "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": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/8a1873d9d72ecfafc513af415987204d057c97729295393d3137a51b3e66fb13.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": "8a5e1d54554673f2e4b6f8f8c67da48b3b4f3e53d2d418c8aca92f1f527c6668", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f9a8bf9361c83e250080cd6600d05fda1bd28906afe7684d480ebfd4ddda50da", "generation_seconds_batch": 13.596160667017102, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4944247007369995, "target_z": 0.5546875189961198, "ce": 6.078212261199951, "genuineness": 3.8922953605651855, "identity": 0.6859775185585022, "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_Disgust/8a5e1d54554673f2e4b6f8f8c67da48b3b4f3e53d2d418c8aca92f1f527c6668.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "8a6dc288e12d01c6edb45d7481503b0b70037f4b4a993664328edf403ab90c35", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "dba29e8ca14c84cbad06a94650ee861a4fe82c5dcc25855c84eb3fcc01c7c5f8", "generation_seconds_batch": 18.630914609064348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07980190217494965, "target_z": -0.2910156316486419, "ce": 5.188632965087891, "genuineness": 3.835810661315918, "identity": 0.4191865026950836, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.", "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_Disgust/8a6dc288e12d01c6edb45d7481503b0b70037f4b4a993664328edf403ab90c35.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "8a8ccb3d866b46531ee24b5d9f7f807fe678392c2efdbe9f39965ca049c440ab", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cf7538585a792247f3b412d1f972a37986f2ffd93ecbe2adba4884db0bea88dc", "generation_seconds_batch": 20.48421991802752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0456693172454834, "target_z": 3.7187500455906877, "ce": 6.086154937744141, "genuineness": 3.6475296020507812, "identity": 0.5085296630859375, "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_Disgust/8a8ccb3d866b46531ee24b5d9f7f807fe678392c2efdbe9f39965ca049c440ab.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "8b13093d64762c0900416a72fc167a4edd634d0be262d32d065de17bad315b73", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "67d563aa1549d715025550c363ed764bb735cf93330ecfbb1d92affea77e0f81", "generation_seconds_batch": 18.992993233026937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33834266662597656, "target_z": 0.23632811265252213, "ce": 6.252951145172119, "genuineness": 4.061748504638672, "identity": 0.6072337627410889, "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_Disgust/8b13093d64762c0900416a72fc167a4edd634d0be262d32d065de17bad315b73.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "8cc430b2fb7f52316bcf98e37254ce67afa86d8afed836f2e3bce7775a13313f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b779d0e4752b7ae1f61d27c41da657c912cb8621d01ecbcaaee88bd741a37dcb", "generation_seconds_batch": 14.838319631991908, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1181042417883873, "target_z": -0.21289062405019402, "ce": 6.2767791748046875, "genuineness": 4.168440818786621, "identity": 0.6175074577331543, "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_Disgust/8cc430b2fb7f52316bcf98e37254ce67afa86d8afed836f2e3bce7775a13313f.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "8ccab9e7d9c6df080e4332fcd535eec558c4baea4ff6d21555058330430f1db6", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b5031cd45b4d38570979a1c484fb6299035434143a8c71b86652c504a3797d16", "generation_seconds_batch": 18.684818823938258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01116614043712616, "target_z": -0.47656249620077606, "ce": 6.0305562019348145, "genuineness": 4.557555198669434, "identity": 0.5383775234222412, "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_Disgust/8ccab9e7d9c6df080e4332fcd535eec558c4baea4ff6d21555058330430f1db6.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "8dadff50359c1c16e86515e81418c7877a1e3898a2e0a094f14fe4dc65de5938", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a3735aa7c16d784b9c6ef482a43ebfd80729958e200274ac7971bf3322e73629", "generation_seconds_batch": 18.781612343969755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010857701301574707, "target_z": -0.431640624050194, "ce": 6.1020402908325195, "genuineness": 4.507347106933594, "identity": 0.5950304269790649, "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_Disgust/8dadff50359c1c16e86515e81418c7877a1e3898a2e0a094f14fe4dc65de5938.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "8dbc50d4f4449ef6ba9e0f7beed971f742a2ca66bc7bb59ed2482bcb8f2d13ab", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c66f316d8a98fb340e4c92c68f70b3144cb12cb47a4ad22544a2cc7df9103dfc", "generation_seconds_batch": 21.717241630074568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06735365092754364, "target_z": -0.3164062405019401, "ce": 6.38797664642334, "genuineness": 4.720732688903809, "identity": 0.6544952392578125, "hypothesis": "Die Tür 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_Disgust/8dbc50d4f4449ef6ba9e0f7beed971f742a2ca66bc7bb59ed2482bcb8f2d13ab.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "8dcf66b67a059cae90e935721b79e00bfbf10a165bc821dc0e6265e8b027e826", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0aa39f85145f1f4e2310e5e769428edda701122535ee56273efb377e28efb602", "generation_seconds_batch": 18.8602177829016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.593701720237732, "target_z": 2.796874977204656, "ce": 5.967014789581299, "genuineness": 3.6789097785949707, "identity": 0.5661859512329102, "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_Disgust/8dcf66b67a059cae90e935721b79e00bfbf10a165bc821dc0e6265e8b027e826.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": "8de8bb395b7f05125025ee0f3f247f31864c2c196f96bda03cdf0541ebd6a0a9", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "3646be04802f26c092ec8ca45c600cd0a31ded96c5ec02f599f16ba6c3713939", "generation_seconds_batch": 15.15155573701486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0663960874080658, "target_z": -0.318359375949806, "ce": 5.855817794799805, "genuineness": 4.017816066741943, "identity": 0.7774724960327148, "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": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/8de8bb395b7f05125025ee0f3f247f31864c2c196f96bda03cdf0541ebd6a0a9.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "8deb6abf56abd9973a9dbdfbd5fd91a7afc182e7f10557ab0730fb1c932c2674", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c262d70e01d22a5718ea17aea537b3afe08faf02c9a931436f0c3ef635a5203a", "generation_seconds_batch": 13.966939782025293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01564548909664154, "target_z": -0.4218750075984479, "ce": 6.038498878479004, "genuineness": 4.607763767242432, "identity": 0.6469241380691528, "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_Disgust/8deb6abf56abd9973a9dbdfbd5fd91a7afc182e7f10557ab0730fb1c932c2674.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "8e79f169b51e95726fdaf9d56ddd9f6bcb03f79c17dd0cbbcbe5b11ef5e757bc", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9dda9fa82645549432da97027ddb86bbf7b2afda925fac70f0fb007fd5005f30", "generation_seconds_batch": 19.984008742962033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0663960874080658, "target_z": -0.318359375949806, "ce": 6.284721851348877, "genuineness": 4.143336772918701, "identity": 0.8549710512161255, "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_Disgust/8e79f169b51e95726fdaf9d56ddd9f6bcb03f79c17dd0cbbcbe5b11ef5e757bc.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": "8eaf4282e2647a83b04b11057ef927a54490b2680a086cd20af2b6cb2030f9e7", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "81e5d73e6d67adf95ab261f77d7c088e4f1c7b8ee2582523ccdb196b12b02a7f", "generation_seconds_batch": 14.220813627936877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05011759698390961, "target_z": -0.35156249620077606, "ce": 6.213237762451172, "genuineness": 4.268857479095459, "identity": 0.5224592685699463, "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_Disgust/8eaf4282e2647a83b04b11057ef927a54490b2680a086cd20af2b6cb2030f9e7.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": "8f31b7ad88350adfa29248d70c69a1bf953214f1fbfdb66de4f5628b13bbd124", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5b684f91c9cf65b1b1a709b69bb0cb4e441f2dd657fd8ae3db7c0845af524d35", "generation_seconds_batch": 18.636817859951407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1647155284881592, "target_z": 1.9218749164170728, "ce": 5.804190158843994, "genuineness": 3.7667744159698486, "identity": 0.3562776446342468, "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_Disgust/8f31b7ad88350adfa29248d70c69a1bf953214f1fbfdb66de4f5628b13bbd124.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": "8f3ce209f0e2cb247616b79576792ae1185017e4e273c90f58c5b39e6ebf6cee", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The road turns left behind the bridge.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "146bf0d5484224d32aa2ca152a70ac84c2d19f9815583ec1daaef547d3a0488a", "generation_seconds_batch": 13.61094427399803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42260780930519104, "target_z": 0.40820312025097005, "ce": 5.871703147888184, "genuineness": 3.327451705932617, "identity": 0.23003169894218445, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other's", "wer": 0.08333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/8f3ce209f0e2cb247616b79576792ae1185017e4e273c90f58c5b39e6ebf6cee.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "8f50ced2cc27dc9467cca64187423b8b5b50738ba4c732b2716fa32924ed1b24", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "86f6d0166d6cfb01aef029ffa8bfcdc77b1a5241f8ca2cc34ef83022af62b212", "generation_seconds_batch": 18.921585524920374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06160829961299896, "target_z": -0.3281249924015521, "ce": 5.879645347595215, "genuineness": 4.086852550506592, "identity": 0.7321091890335083, "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_Disgust/8f50ced2cc27dc9467cca64187423b8b5b50738ba4c732b2716fa32924ed1b24.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "8f806cba75ef4daaf203d8544ba62b3cbb42a4e52653fd8f278f825d55ad34a8", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a2679dbef6fc796304937a64e9c5a445563f9477511bb9f191f86b4fe553a69a", "generation_seconds_batch": 13.888030471047387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5327270030975342, "target_z": 0.6328124506100885, "ce": 5.808161735534668, "genuineness": 3.9801597595214844, "identity": 0.6632527112960815, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/8f806cba75ef4daaf203d8544ba62b3cbb42a4e52653fd8f278f825d55ad34a8.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "90222d25de4d99d986a85c2dcf2431bb1499615e70b9251da685f805ac94388d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0cd4a11113ee5fbcbfa65bd63ccdb26ded1e045904b2a6f0bb44baf70165c687", "generation_seconds_batch": 18.958396796952, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06352341175079346, "target_z": -0.32421875189961197, "ce": 5.80021858215332, "genuineness": 4.218649387359619, "identity": 0.3715640902519226, "hypothesis": "Ich hab des, ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.25, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/90222d25de4d99d986a85c2dcf2431bb1499615e70b9251da685f805ac94388d.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "905d221f24dc5d2100f1ba4de49a110f3638776801c1ee01974af6aa574cb82a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "efbdd5a3885cc67b10d282302869fe2a94ff51424f9b49439cc8e88f1c98f393", "generation_seconds_batch": 13.685686188051477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.06095917522907257, "target_z": -0.5781249924015521, "ce": 6.229123115539551, "genuineness": 4.557555198669434, "identity": 0.670236349105835, "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_Disgust/905d221f24dc5d2100f1ba4de49a110f3638776801c1ee01974af6aa574cb82a.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": "90c3e874d02e12e111c6554fd5d1c767402eab915fc0047e018d903a736fb83f", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cefaeafe7d9ee3fcb765bf29ee08c82b654917cbf12574065454b3f088b3576f", "generation_seconds_batch": 13.76190192392096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3945295810699463, "target_z": 2.390624992401552, "ce": 6.268836498260498, "genuineness": 3.6349775791168213, "identity": 0.6617045402526855, "hypothesis": "Je beri kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/90c3e874d02e12e111c6554fd5d1c767402eab915fc0047e018d903a736fb83f.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": "9113bbe100f72964c4ff3760d13964827eab1b92622cb4d93c45205efa6c35b3", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The road turns left behind the bridge.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e33dbda0bbd9fcf97eac473c071461cb19df856fbee54e4e7b6f5ea32b46bd3e", "generation_seconds_batch": 15.824438930954784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2751438021659851, "target_z": 0.10742184175679034, "ce": 6.252951145172119, "genuineness": 3.7542223930358887, "identity": 0.2863308787345886, "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_Disgust/9113bbe100f72964c4ff3760d13964827eab1b92622cb4d93c45205efa6c35b3.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "913cc5f040a9dd5bb598d9dd2288f8764d16e64a37cb5adcb1f4e7de5ee38e1a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dc4ead2b24ffabbb2845dd999e5b3340474285717eb1e291a4055f187e2a7050", "generation_seconds_batch": 15.669875820050947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1449158787727356, "target_z": -0.15820312025097005, "ce": 6.1894097328186035, "genuineness": 4.250029563903809, "identity": 0.811927855014801, "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_Disgust/913cc5f040a9dd5bb598d9dd2288f8764d16e64a37cb5adcb1f4e7de5ee38e1a.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "914037a86cdd7cb809d9f32219ea4819473e31a9d5011fb231b978fc5dd5cf38", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "54a4d7b3582e8b2aad2d9b297d85d02fd45cafeee32f7c751763619c69bd36de", "generation_seconds_batch": 18.645328357000835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7009483575820923, "target_z": 3.015625174764302, "ce": 6.1020402908325195, "genuineness": 3.8044304847717285, "identity": 0.6416128873825073, "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_Disgust/914037a86cdd7cb809d9f32219ea4819473e31a9d5011fb231b978fc5dd5cf38.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "9152e41511ff70994a265f858905d4bfec01e13acc4e03ca86ceb83c87f00592", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6f569d13bbbb532d4005a03993b750761bd3a86426766cc9c6e94c4839cb4eba", "generation_seconds_batch": 18.786491008941084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.103091761469841, "target_z": -0.6640625265945678, "ce": 6.403861999511719, "genuineness": 4.425758361816406, "identity": 0.46950578689575195, "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_Disgust/9152e41511ff70994a265f858905d4bfec01e13acc4e03ca86ceb83c87f00592.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "91b02a5cf9bb2b9a8d4b7379d86ed7139a9a897e507fbbea34bd93342f66effe", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bc79d62129badcf02d3e53e63b5f08bd0c90387eec0d4ccd28a453fc42b1f0b2", "generation_seconds_batch": 19.716223273891956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.049468472599983215, "target_z": -0.5546874886023281, "ce": 6.38003396987915, "genuineness": 4.3127899169921875, "identity": 0.5372003316879272, "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_Disgust/91b02a5cf9bb2b9a8d4b7379d86ed7139a9a897e507fbbea34bd93342f66effe.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "91dadc87ab7fa8458833bd47e9b7073d9db8a9d1e3a41bb1f4e9bc630e455981", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9b57c4f7a4971088bf1a3f0821e50003223fdd31ffbff4484d70ef782358235f", "generation_seconds_batch": 18.72762227698695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.028402194380760193, "target_z": -0.511718751899612, "ce": 6.4912309646606445, "genuineness": 4.6956281661987305, "identity": 0.5668898224830627, "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_Disgust/91dadc87ab7fa8458833bd47e9b7073d9db8a9d1e3a41bb1f4e9bc630e455981.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": "922362fd9370d5b25b4e655f1b9c9e0884fc7cb9ba0a6e2c9cf5e51bdd34f542", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4465f6718af5e5e05e5db8f515cdef32dd19a57dcee02dd0cdb4ff056883e89", "generation_seconds_batch": 13.632788104005158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9732038974761963, "target_z": 1.5312500151968957, "ce": 5.0754499435424805, "genuineness": 3.5722172260284424, "identity": 0.2989465594291687, "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_Disgust/922362fd9370d5b25b4e655f1b9c9e0884fc7cb9ba0a6e2c9cf5e51bdd34f542.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": "9271618f59f6ad517fe64bc5b07cff2d97b9447d38e0c8e0675891ce0c0b1c24", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Someone moved the little blue chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "1a693505a0cf903f97191106fb64fce3f8fc56fc1a495489215efdea7649d77f", "generation_seconds_batch": 13.737125792889856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0252210795879364, "target_z": -0.40234374430116404, "ce": 6.316492557525635, "genuineness": 3.9550557136535645, "identity": 0.32049232721328735, "hypothesis": "Someone moved the little blue chair. It used to stand here. Beside the tall bookshelf. We can put it back after lunch.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/9271618f59f6ad517fe64bc5b07cff2d97b9447d38e0c8e0675891ce0c0b1c24.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "92c83a8e390931e0dc64ebd806d5715a4919d0fa79ce2cd78bb68b8b41469fa1", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ede7ada148765a3569df711f5e6a3b86ef0dd3415c82aa88c3ccce932ea95197", "generation_seconds_batch": 13.596878854907118, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0252210795879364, "target_z": -0.40234374430116404, "ce": 5.998785495758057, "genuineness": 4.1998209953308105, "identity": 0.6060214638710022, "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_Disgust/92c83a8e390931e0dc64ebd806d5715a4919d0fa79ce2cd78bb68b8b41469fa1.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "934884826e5818d81536e89568ed526c394711dd5b294ce09b96424fb111995a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "69fbabe640b7ec385969cb7a03cec7b6d91428c7de81f3e1af0131fee6fbf253", "generation_seconds_batch": 18.963159556034952, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.002548113465309143, "target_z": -0.4589843683513581, "ce": 6.149696350097656, "genuineness": 4.645420074462891, "identity": 0.6672753095626831, "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_Disgust/934884826e5818d81536e89568ed526c394711dd5b294ce09b96424fb111995a.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "935fb43f0e73d719f4c2db7c53a410220a91764b8d612ba2b5641cae3635bf60", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f7839886888c39b07fce34666572edc5c9fb18d12e753d850499fd3c340c6135", "generation_seconds_batch": 18.64124210504815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8889387249946594, "target_z": 1.3593749468108645, "ce": 6.197352409362793, "genuineness": 3.923675537109375, "identity": 0.7570568919181824, "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_Disgust/935fb43f0e73d719f4c2db7c53a410220a91764b8d612ba2b5641cae3635bf60.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "9365cf5872470ba32411807d10c9161520b58ed1a4b4bb038a9b0ce5de44d079", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "87429f89ebb0d8fa8029f8359f0f82d6960a9cec04fa0c309994e29cc0919a44", "generation_seconds_batch": 18.679843944031745, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1110923290252686, "target_z": 1.8125000607875834, "ce": 6.086154937744141, "genuineness": 3.9173994064331055, "identity": 0.6287347078323364, "hypothesis": "De deug 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_Disgust/9365cf5872470ba32411807d10c9161520b58ed1a4b4bb038a9b0ce5de44d079.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "93bfcb0c176dfaab547e44666c79f70691dc2cdda75a0c1afd2692ffb2674a69", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "ca97d6731663275a670efdad8cf32edba35deb70230b17215046b7cccf5eb26f", "generation_seconds_batch": 18.76773109298665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.835315465927124, "target_z": 1.2499999696062083, "ce": 5.9431867599487305, "genuineness": 3.8169827461242676, "identity": 0.6998966932296753, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/93bfcb0c176dfaab547e44666c79f70691dc2cdda75a0c1afd2692ffb2674a69.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": "94104efa01ca580c3002e7be1d3d058618c2df4f924960ec3c4668e22a15d601", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bfb7b88b37bc1c8fb80c27befd7507cfc60b62e26ec9063dd0881e1fd678d13f", "generation_seconds_batch": 14.52495331200771, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11140133440494537, "target_z": -0.22656249620077604, "ce": 6.1020402908325195, "genuineness": 4.444586753845215, "identity": 0.6701992750167847, "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_Disgust/94104efa01ca580c3002e7be1d3d058618c2df4f924960ec3c4668e22a15d601.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "94f05caddbcfd7ae61cb26b0f8e7426c688f48fb66d8c9e5ae19b2bd9a63e1fa", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "b6f6bf534556cad002de2a03180eefdf595d98bb23dc4388b16b1fc64f588880", "generation_seconds_batch": 20.186467583989725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0060699135065078735, "target_z": -0.4414062405019401, "ce": 6.0146708488464355, "genuineness": 4.507347106933594, "identity": 0.5966524481773376, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/94f05caddbcfd7ae61cb26b0f8e7426c688f48fb66d8c9e5ae19b2bd9a63e1fa.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": "9530ad9cf32b745cdb60370e17633e8e0f18b14d9b5fd0bf569a523342259b01", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ad6b8233ec7192de9713cc1722cf2c2666d2665b9a5fb56f1069a2111d0b32f2", "generation_seconds_batch": 18.54399111389648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5097455978393555, "target_z": 0.5859374430116405, "ce": 5.998785495758057, "genuineness": 3.6851859092712402, "identity": 0.630707859992981, "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_Disgust/9530ad9cf32b745cdb60370e17633e8e0f18b14d9b5fd0bf569a523342259b01.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "95366ca76286090fd745378ec4ce6b0335b755d908b7d13b1bbc95cc1e5eb6a3", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f760aeb54e667748760b125964801111dea8d243124d09945129fbc8ee9be76b", "generation_seconds_batch": 18.99569412402343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1286373734474182, "target_z": -0.19140627089573178, "ce": 6.229123115539551, "genuineness": 4.482243061065674, "identity": 0.6196002960205078, "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_Disgust/95366ca76286090fd745378ec4ce6b0335b755d908b7d13b1bbc95cc1e5eb6a3.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "954083c1f6cf2d88a4547ceb319133faf55ae88fc5a32e911348e0834bffbd55", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b2f1f73f138360104e0929ae8847f9747cd0b0c9f5726ddc07445174c7d84d4b", "generation_seconds_batch": 18.682836029911414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0893774926662445, "target_z": -0.2714843683513581, "ce": 6.213237762451172, "genuineness": 4.168440818786621, "identity": 0.5118099451065063, "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_Disgust/954083c1f6cf2d88a4547ceb319133faf55ae88fc5a32e911348e0834bffbd55.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "95a5cf92bc74cfad8fc76a0014bcecc55af5133a663c124d9ea2fcb192db935d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "169432fd5eedea60685407f401f0034b0e8e07c68d5431339251ed272f2b9b82", "generation_seconds_batch": 20.986065687029622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2919010818004608, "target_z": 0.14160154492858917, "ce": 6.38797664642334, "genuineness": 4.137060642242432, "identity": 0.6988316774368286, "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_Disgust/95a5cf92bc74cfad8fc76a0014bcecc55af5133a663c124d9ea2fcb192db935d.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "95ddd457f3c3d33744787f38bdcd938232d5f8c335cd10d4074c9824b658ef93", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "378694e10f23e42f110e64b50d6d2ad71286dd8739c11fd0c34a511a6756f631", "generation_seconds_batch": 13.596878854907118, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07309900224208832, "target_z": -0.30468748860232814, "ce": 6.205295085906982, "genuineness": 4.469690799713135, "identity": 0.6895572543144226, "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_Disgust/95ddd457f3c3d33744787f38bdcd938232d5f8c335cd10d4074c9824b658ef93.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "9649fe2c3b2ab0dad89a17cffabe9adb1841ba8c89b7dc5e64459aa206d26e50", "bucket": "emo_Disgust", "phase": "wording", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a48d44f9beddabd46e7dcf8d85908b0eb5f36b2abd3fb897099d69589b11da37", "generation_seconds_batch": 16.536070364993066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.026487082242965698, "target_z": -0.5078125113976719, "ce": 6.316492557525635, "genuineness": 4.507347106933594, "identity": 0.3756369948387146, "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_Disgust/9649fe2c3b2ab0dad89a17cffabe9adb1841ba8c89b7dc5e64459aa206d26e50.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": "966538d200d90e1b038a54b39e4a998e01307a363d4da2705f4118004341b803", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5198292653e58cd43855dbef500894df8d7d5c79db632ba96d595c56475105ce", "generation_seconds_batch": 13.63742102496326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3638877868652344, "target_z": 2.3281251443705107, "ce": 5.8875885009765625, "genuineness": 3.5063188076019287, "identity": 0.7619181871414185, "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_Disgust/966538d200d90e1b038a54b39e4a998e01307a363d4da2705f4118004341b803.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "968bd0f99ad19ff619ba470de3d21bb8ecaf7869b0ade180e64cf564ad3b9c48", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "096b237aa8b659d4bb88d71e88b9ab630f18cb6a9640899813da0f617dc5a7c9", "generation_seconds_batch": 21.344437616993673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0022396743297576904, "target_z": -0.44921875189961197, "ce": 6.2767791748046875, "genuineness": 3.9048471450805664, "identity": 0.34013450145721436, "hypothesis": "The 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_Disgust/968bd0f99ad19ff619ba470de3d21bb8ecaf7869b0ade180e64cf564ad3b9c48.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "96cd2f669d660e3506df0f044aa60ee08324da1b97e66136fcaa6f05c6483542", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "fc77343201e20857bcfcf6e2ca39ee85d7ca2d7ecf71fd373d67fc2afae21c7f", "generation_seconds_batch": 19.00804268300999, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03606267273426056, "target_z": -0.5273437746949557, "ce": 6.300607204437256, "genuineness": 4.394378662109375, "identity": 0.6908714771270752, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/96cd2f669d660e3506df0f044aa60ee08324da1b97e66136fcaa6f05c6483542.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "96d8026aac2f02e47c06fdac55f56c440dafd0051ba5a6deb3941c469c017611", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e341e846db3e35b434de3491aa043a4c154e509a728f5a54734f3c96c12ab76a", "generation_seconds_batch": 18.660559147945605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07118387520313263, "target_z": -0.3085937594980599, "ce": 6.046441555023193, "genuineness": 4.607763767242432, "identity": 0.5676330327987671, "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_Disgust/96d8026aac2f02e47c06fdac55f56c440dafd0051ba5a6deb3941c469c017611.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "96f6415bda7ef248c8bfc3d3bfb5f296872b0e3992d1ebc0692fd5dbfdb6b9a9", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1153990b085c2fe424d0d62696a357f48451678ecda64bd524c5d9f8ae77331f", "generation_seconds_batch": 19.56028770795092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08075946569442749, "target_z": -0.28906249620077606, "ce": 6.1894097328186035, "genuineness": 4.231201171875, "identity": 0.7315117120742798, "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_Disgust/96f6415bda7ef248c8bfc3d3bfb5f296872b0e3992d1ebc0692fd5dbfdb6b9a9.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "972e2bd134ef3f19e62381ed8b1eda2fb220260e26997db900017352de0a5d2c", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "96f848a774ecdf5d4fe3c858499c124d45305d9da0af15b7a5768b5b36ab3ab3", "generation_seconds_batch": 19.786264849011786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06926876306533813, "target_z": -0.3125, "ce": 6.173524379730225, "genuineness": 3.898571252822876, "identity": 0.45261335372924805, "hypothesis": "The 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_Disgust/972e2bd134ef3f19e62381ed8b1eda2fb220260e26997db900017352de0a5d2c.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": "975fea5868794e31ed72fbf0e8c0afa4e2a106b1648f375b62b55020f98747bc", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "d0c1f808157c40ba85caf208633cd6161ae263f1c0222782ff7a3f36750e36f2", "generation_seconds_batch": 18.746871241019107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16598215699195862, "target_z": -0.11523438354825391, "ce": 6.221180438995361, "genuineness": 3.7667744159698486, "identity": 0.7446063160896301, "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": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/975fea5868794e31ed72fbf0e8c0afa4e2a106b1648f375b62b55020f98747bc.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": "97dc499d362042bf079ecfcd510d08cc1cf01bdbf15bb2dc02e77b22a4ec69f8", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "51e8dc70e708665268cfcb60867bdc590db3ba5e91f4aa6d2456fe052ca553a6", "generation_seconds_batch": 13.7897016890347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2559926509857178, "target_z": 0.06835937594980598, "ce": 6.260893821716309, "genuineness": 4.369274139404297, "identity": 0.8012497425079346, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/97dc499d362042bf079ecfcd510d08cc1cf01bdbf15bb2dc02e77b22a4ec69f8.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "9858a5d0884739e6d22ce9b290963ae5dff8e31d3ae12344e96ee63501d3d032", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6c90d6c5ad3c620d4ef316e427f26515aa60579495268a1f1d1c317bdfebe255", "generation_seconds_batch": 19.421046264935285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09608039259910583, "target_z": -0.25781251139767186, "ce": 6.181467056274414, "genuineness": 4.331617832183838, "identity": 0.4894964098930359, "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_Disgust/9858a5d0884739e6d22ce9b290963ae5dff8e31d3ae12344e96ee63501d3d032.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "98f60afb5c6cd903540d151bb386f9071a404f6352540ef209d5e1dc63adce80", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ffc2826192759ac72250da255851f83bd417e9b90789a213be3e2ce01caa5a59", "generation_seconds_batch": 18.81578950607218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11714668571949005, "target_z": -0.21484374430116407, "ce": 5.927301406860352, "genuineness": 3.8797430992126465, "identity": 0.5739767551422119, "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_Disgust/98f60afb5c6cd903540d151bb386f9071a404f6352540ef209d5e1dc63adce80.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "990c032a289fbaf5241a6b82b29cb7f16ec5790a682bdae6e80d2f4420df5532", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8bf0357091928011c397a6500d54d279795888290941c535de4b63b6d82be55c", "generation_seconds_batch": 21.38089499704074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022348403930664062, "target_z": -0.40820312025097005, "ce": 6.213237762451172, "genuineness": 4.093128204345703, "identity": 0.6407824158668518, "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_Disgust/990c032a289fbaf5241a6b82b29cb7f16ec5790a682bdae6e80d2f4420df5532.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "990fd1756de6d11e9dce1f8b47e7c93e55dfe6fcbe2a54566414b5cc67f429b8", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7731e8e01ac4a9135f583ef86138a924d838f02d10461af4c7a293064b8d4c6f", "generation_seconds_batch": 18.993471857043914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17268507182598114, "target_z": -0.10156249620077604, "ce": 6.2767791748046875, "genuineness": 4.557555198669434, "identity": 0.49858397245407104, "hypothesis": "Die Tür 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_Disgust/990fd1756de6d11e9dce1f8b47e7c93e55dfe6fcbe2a54566414b5cc67f429b8.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "99523720dd1bddc5498d56c59de41a4f934b99f6bf0503c94e62bea8a2db9e5e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "415e8fddc06287571eadcbbaa54d58acedc9f1bcf16c2c96c3c510df1ad2bb55", "generation_seconds_batch": 19.59495813504327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09608039259910583, "target_z": -0.25781251139767186, "ce": 6.260893821716309, "genuineness": 4.005263805389404, "identity": 0.3081229329109192, "hypothesis": "The 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_Disgust/99523720dd1bddc5498d56c59de41a4f934b99f6bf0503c94e62bea8a2db9e5e.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "9952bcddc89838563ff45e3e809f09657035e485d5bbadb76180642f46448d68", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "462b65d53c6d8bc122d1d8a33518ed3aabdf2743ec70a46cdb09038347608186", "generation_seconds_batch": 13.764533638954163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7698925733566284, "target_z": 3.156250197559646, "ce": 5.792276382446289, "genuineness": 3.7416701316833496, "identity": 0.5449522137641907, "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_Disgust/9952bcddc89838563ff45e3e809f09657035e485d5bbadb76180642f46448d68.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "999f69df5fd9eefb9c5de70c389f179bcb4a805e6aedbfbedea17167db2fadd0", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2e28ed8cf668277f847b70f7e4b76dee96feb668ccd8ec84a989fa392dd4a765", "generation_seconds_batch": 18.920137204928324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21673275530338287, "target_z": -0.01171875189961198, "ce": 6.117925643920898, "genuineness": 3.722842216491699, "identity": 0.47277945280075073, "hypothesis": "The 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_Disgust/999f69df5fd9eefb9c5de70c389f179bcb4a805e6aedbfbedea17167db2fadd0.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "7cbd441b2ba012c22eb86ec81e4986bee9b07f6e20c102528ab83de295329ead", "generation_seconds_batch": 15.858885405934416, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055862948298454285, "target_z": -0.33984374430116404, "ce": 6.23706579208374, "genuineness": 4.632867813110352, "identity": 0.22310444712638855, "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_Disgust/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.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": "9aa23c2e74c192a970aeffb08d4f5772366547e0b10b61328d3de3ba920b9efe", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "48244bda29f22180952e7982436c3fec7515704875edba80c2d308dadb38917e", "generation_seconds_batch": 19.641047214972787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7162692546844482, "target_z": 3.046875098779823, "ce": 5.959072113037109, "genuineness": 3.6349775791168213, "identity": 0.6195750832557678, "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_Disgust/9aa23c2e74c192a970aeffb08d4f5772366547e0b10b61328d3de3ba920b9efe.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "9afbe39dca71fcb1252e3f87c7add4c01dd3fa897bd4263fb97df852632b5603", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f1823b039da7e9823103b1b1472000d90086a5325d62eedc51c133b5fb11de47", "generation_seconds_batch": 13.888030471047387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38143280148506165, "target_z": 0.32421875189961197, "ce": 6.125868320465088, "genuineness": 4.250029563903809, "identity": 0.4974370002746582, "hypothesis": "Die Tür 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_Disgust/9afbe39dca71fcb1252e3f87c7add4c01dd3fa897bd4263fb97df852632b5603.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "9afc2f5c4310ff9f6dcc02c7882b9e9da70f973a4d3690956a5871dfa612ebe0", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b643dceba07f7fc84e18ba1e2ddefd73d9df3091680c138d1439111be9ff8922", "generation_seconds_batch": 18.944341050926596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06926876306533813, "target_z": -0.3125, "ce": 6.173524379730225, "genuineness": 4.344170093536377, "identity": 0.629510760307312, "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_Disgust/9afc2f5c4310ff9f6dcc02c7882b9e9da70f973a4d3690956a5871dfa612ebe0.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "9b35a2b25575b6f832933a079a130fd0a57c5a5edaae2cdf28a26a62fc742060", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0f373c97cf9181626270efd2f72d401233391b0140bc69f4c8a119862758fe3d", "generation_seconds_batch": 18.8172981350217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.046287357807159424, "target_z": -0.3593750075984479, "ce": 5.6334228515625, "genuineness": 4.319066047668457, "identity": 0.6715354919433594, "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_Disgust/9b35a2b25575b6f832933a079a130fd0a57c5a5edaae2cdf28a26a62fc742060.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": "9b599c13b3885cb6377411c546f780bb5d86ba002842e6aea831d2f20c98e023", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2eddb38f1b85a1a28b9fe90dd825c8c62b0318d4521ef093b70550cf809bb978", "generation_seconds_batch": 13.666668714024127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06735365092754364, "target_z": -0.3164062405019401, "ce": 5.927301406860352, "genuineness": 4.469690799713135, "identity": 0.6720225811004639, "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_Disgust/9b599c13b3885cb6377411c546f780bb5d86ba002842e6aea831d2f20c98e023.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "9bd2e6fa66f179506a1860b0ba2ffc093972bd376248c453837dfa7ff6615532", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "7f7e404c534811341ce03026961285648516ac85e887ad0f75f09204a312319d", "generation_seconds_batch": 13.845715211005881, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.04372312128543854, "target_z": -0.5429687367027162, "ce": 6.284721851348877, "genuineness": 3.8546390533447266, "identity": 0.38703036308288574, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/9bd2e6fa66f179506a1860b0ba2ffc093972bd376248c453837dfa7ff6615532.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "9bfb31f884fb29eec77ef6b92b8a95b00870a8e532d6669997857b3c9e0503b8", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "89502e25f568a1298d3b0b405ee810511cc8134043472b4571b14bc5868ea77a", "generation_seconds_batch": 19.786264849011786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06065073609352112, "target_z": -0.330078127849418, "ce": 6.062326908111572, "genuineness": 3.7542223930358887, "identity": 0.5063679218292236, "hypothesis": "The 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_Disgust/9bfb31f884fb29eec77ef6b92b8a95b00870a8e532d6669997857b3c9e0503b8.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "607cf344d1878f5144ce6b240350a60739e26c49dbc79a392239f67013dea7ed", "generation_seconds_batch": 14.035717035993002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.042457133531570435, "target_z": -0.36718748860232814, "ce": 6.300607204437256, "genuineness": 4.281409740447998, "identity": 0.6749691963195801, "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_Disgust/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "9c101e03f4907416f68d9aade633b5cd0b533e6e8f31d623e232eadbd3af06dc", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ab01bde7518301105e70a6aec436b9b0346103144e0c0fbcafa731e872562045", "generation_seconds_batch": 18.92304601892829, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10230452567338943, "target_z": -0.24511719177412697, "ce": 6.372091293334961, "genuineness": 4.381826400756836, "identity": 0.5678008794784546, "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_Disgust/9c101e03f4907416f68d9aade633b5cd0b533e6e8f31d623e232eadbd3af06dc.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "9c77bb913f1687f2e41cc7a04f6ab85ea2c03b59635975fd0f174823007fa8d2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7ce4dba371bc1ae476d44bcd1f7293228736b769caad0c72633743489ff36a72", "generation_seconds_batch": 19.251254974049516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030008867383003235, "target_z": -0.392578127849418, "ce": 6.229123115539551, "genuineness": 4.607763767242432, "identity": 0.8052475452423096, "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_Disgust/9c77bb913f1687f2e41cc7a04f6ab85ea2c03b59635975fd0f174823007fa8d2.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc7ad602bf5a1f05a341241fe4ec9d0dd8df73eca5944bae70efd2c3a1fb0483", "generation_seconds_batch": 13.733267979929224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06256584823131561, "target_z": -0.3261718873474779, "ce": 6.316492557525635, "genuineness": 4.7458367347717285, "identity": 0.7013581991195679, "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_Disgust/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "9ca0e6bde375ef944484cc1fda1816363103de8b0a813aefce7e5f7cfd644039", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "395c7a3311460ce844707bf24d1f06b5a92e81cd5c45e9c8a31b7ea81f8d8b44", "generation_seconds_batch": 18.925945125054568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009900137782096863, "target_z": -0.4335937594980599, "ce": 5.8875885009765625, "genuineness": 4.519899368286133, "identity": 0.42543351650238037, "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_Disgust/9ca0e6bde375ef944484cc1fda1816363103de8b0a813aefce7e5f7cfd644039.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "9d132d565193396c39074740f63c9f3fa7a433387b5706c8661e9d21f69525c5", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "001b3b7b3ead10c5331a1aec7257badd09d168a1de2a158a07095abb79c66a77", "generation_seconds_batch": 19.14165495103225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07022632658481598, "target_z": -0.3105468645521341, "ce": 6.0146708488464355, "genuineness": 4.432034492492676, "identity": 0.6767536401748657, "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_Disgust/9d132d565193396c39074740f63c9f3fa7a433387b5706c8661e9d21f69525c5.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": "9d4516ec33180f4cc4b24b2ac26f6cced76116a7ddd7eaa3ddff88bf27b6f6f7", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d402a8611c540f3545daabc8f81d9d0f216a23a0db9356c79f4306a6b2008783", "generation_seconds_batch": 13.7897016890347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5553994178771973, "target_z": 2.7187500455906877, "ce": 6.213237762451172, "genuineness": 3.9550557136535645, "identity": 0.4957953989505768, "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_Disgust/9d4516ec33180f4cc4b24b2ac26f6cced76116a7ddd7eaa3ddff88bf27b6f6f7.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "9d6f210a3702b34ca046385a7c19844583c7ec40c25b3df0da0fde94c0990231", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d281d7dedf27c2679a040d0fa09d957898b15a94eeb7e17d4a90fa43032bbe22", "generation_seconds_batch": 13.68504132295493, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08841992914676666, "target_z": -0.27343750379922394, "ce": 6.284721851348877, "genuineness": 4.406930446624756, "identity": 0.5520460605621338, "hypothesis": "Die Tür 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_Disgust/9d6f210a3702b34ca046385a7c19844583c7ec40c25b3df0da0fde94c0990231.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": "9d805ff2eaa9a4d0d381ba97067258eae7efc1b4b36be9d66a0d7c8f13ff88c5", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "33dc21618b94f9369fe0841eb6dc49bf0211bf41ec1d726e68430aea1f7a2b6e", "generation_seconds_batch": 13.666668714024127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01756061613559723, "target_z": -0.4179687367027161, "ce": 6.38797664642334, "genuineness": 4.482243061065674, "identity": 0.644996166229248, "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_Disgust/9d805ff2eaa9a4d0d381ba97067258eae7efc1b4b36be9d66a0d7c8f13ff88c5.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "9d9e65e649a443cb4c1310c1107d70832a0754738000d8c87e834ec1c76dd16b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8bc7aee903f2366667ea6dfc83b225dcdc77c27c909cb9389e7a41007e6a6018", "generation_seconds_batch": 20.253823427017778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.06861965358257294, "target_z": -0.5937500151968959, "ce": 6.4912309646606445, "genuineness": 4.68307638168335, "identity": 0.284889817237854, "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_Disgust/9d9e65e649a443cb4c1310c1107d70832a0754738000d8c87e834ec1c76dd16b.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "9e406b18cc22d4efdcd527f7bfa519b2ab0217e6fbb26ac66c7cf22a374c2bac", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3edd713370dbb18dbad08c00ec90fa9ab782a10c71a6d405ea5105d0696c892c", "generation_seconds_batch": 18.722265279036947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02809375524520874, "target_z": -0.3964843683513581, "ce": 6.157639026641846, "genuineness": 4.331617832183838, "identity": 0.8193188309669495, "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_Disgust/9e406b18cc22d4efdcd527f7bfa519b2ab0217e6fbb26ac66c7cf22a374c2bac.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "9ed5901ae62236ff7e6f7c8692d607df3602c28b69717f1bff98ecdf4f63add3", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "262f95909df0ebac75ea431c7c7580c3ebc2f2fce46df58ccce5d997c42eaed8", "generation_seconds_batch": 18.992993233026937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1678972840309143, "target_z": -0.11132811265252213, "ce": 6.1894097328186035, "genuineness": 4.143336772918701, "identity": 0.6330960988998413, "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_Disgust/9ed5901ae62236ff7e6f7c8692d607df3602c28b69717f1bff98ecdf4f63add3.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "9f0c786dff1a4b6f0286c6ea6aee4caf66af9fb16c195748d40d8be9b4a3c840", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "73f04708d014092928c5a3cddddbb1d68a79a1a8b07ad10e9715b656181bb86a", "generation_seconds_batch": 20.26990204397589, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25790777802467346, "target_z": 0.07226564684553778, "ce": 6.0305562019348145, "genuineness": 3.653805732727051, "identity": 0.31279057264328003, "hypothesis": "The 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_Disgust/9f0c786dff1a4b6f0286c6ea6aee4caf66af9fb16c195748d40d8be9b4a3c840.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "a09a352fa4906fc5a80c154ebfad9967adca4a9b464fe5ed5fa276295ac8805f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7eec5338f2c0ec31028f469bfb2282381ba42489d98bb45209c5dac76432f9e9", "generation_seconds_batch": 18.591923584928736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12097691744565964, "target_z": -0.20703124810038803, "ce": 6.348263263702393, "genuineness": 3.3964879512786865, "identity": 0.3286439776420593, "hypothesis": "The 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_Disgust/a09a352fa4906fc5a80c154ebfad9967adca4a9b464fe5ed5fa276295ac8805f.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "a0df84de57f3e7031a92d7c02b11ea51676306b33eb43cc58ec5620766a190c2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6b24cebc41a12495d8076c639f0a2179f8f453ab8dc70a276796f7644ba2966d", "generation_seconds_batch": 19.32708850700874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17555774748325348, "target_z": -0.09570312025097005, "ce": 6.078212261199951, "genuineness": 4.268857479095459, "identity": 0.6502327919006348, "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_Disgust/a0df84de57f3e7031a92d7c02b11ea51676306b33eb43cc58ec5620766a190c2.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "a1755b7c35e6633e0d0292ffbee85df09abff5d16a944d913867d371a5bfd52e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a3cb604a4acd0c12b2f64b3cf5623aeafc5e051b96c0ea626839bd099351320c", "generation_seconds_batch": 21.635261405957863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022348403930664062, "target_z": -0.40820312025097005, "ce": 6.221180438995361, "genuineness": 4.607763767242432, "identity": 0.6950711607933044, "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_Disgust/a1755b7c35e6633e0d0292ffbee85df09abff5d16a944d913867d371a5bfd52e.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "a194ffe8ff899013e72974fe5a92c0efe22cbf222e3f9da99130ad00bb2fcf9a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5da870c27aebf331ed4ba3aa92b8b01691cabce53ca626ea4a47b9409654c543", "generation_seconds_batch": 13.682297415100038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03766933083534241, "target_z": -0.3769531354478659, "ce": 6.229123115539551, "genuineness": 3.9676074981689453, "identity": 0.520221471786499, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.", "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_Disgust/a194ffe8ff899013e72974fe5a92c0efe22cbf222e3f9da99130ad00bb2fcf9a.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "a1fde1276b9c1251e12811ebb03918adc30ab9648e587d503f08ab49c35860a2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "55c11810ca49e0e232fae2011af631cac6367f4152284ffb4191fffbce2c4934", "generation_seconds_batch": 18.927668135031126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08650481700897217, "target_z": -0.27734374430116404, "ce": 6.268836498260498, "genuineness": 4.68307638168335, "identity": 0.6420813798904419, "hypothesis": "Die Tür 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_Disgust/a1fde1276b9c1251e12811ebb03918adc30ab9648e587d503f08ab49c35860a2.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "a242d5d3d1cf780fe8d05e2ae9731b8467bbaae3104d49f82f81089b08d64f1f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a692aecf6c88a0bdbaa364f3de98a81557ca2fbd4fdead66d63a37ecf74f465c", "generation_seconds_batch": 18.72762227698695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0015905648469924927, "target_z": -0.4570312632972839, "ce": 6.427689552307129, "genuineness": 4.356721878051758, "identity": 0.6830782890319824, "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_Disgust/a242d5d3d1cf780fe8d05e2ae9731b8467bbaae3104d49f82f81089b08d64f1f.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "a2475688f6f928a17bd29c06d052235c54315293957829513f80e9ca703d4aaf", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7b10bd7961455ccd502e5a6cce7a4df6d94181f20822189ce19b08df18591551", "generation_seconds_batch": 18.883487040991895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004154786467552185, "target_z": -0.44531251139767186, "ce": 6.356205940246582, "genuineness": 4.645420074462891, "identity": 0.4555164873600006, "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_Disgust/a2475688f6f928a17bd29c06d052235c54315293957829513f80e9ca703d4aaf.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "a36f5b8e8a7eaff7b33837c1a5007bdce9b5e4625951d29874f6d805929dbde5", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "34654eceddd73d97220764a21fc67072469326f3834256796d51ca8097f86b77", "generation_seconds_batch": 18.84210998599883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.06095917522907257, "target_z": -0.5781249924015521, "ce": 6.324435234069824, "genuineness": 4.425758361816406, "identity": 0.4681447744369507, "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_Disgust/a36f5b8e8a7eaff7b33837c1a5007bdce9b5e4625951d29874f6d805929dbde5.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": "a3d4029bd93c781095b03920597241acc810e6ff10e32e7358d56e49783a81b8", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f64a13d62798c1babe51e8eacc08b7dc92b13c5cbdaeaf0bf45bca64dda5c161", "generation_seconds_batch": 13.671508171013556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.489976406097412, "target_z": 4.6250000303937915, "ce": 5.839932441711426, "genuineness": 3.747946262359619, "identity": 0.6643528938293457, "hypothesis": "La route tourne à gauche après le pont, continue jusqu'à la petite barrière en bois. Je t'attenderai 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_Disgust/a3d4029bd93c781095b03920597241acc810e6ff10e32e7358d56e49783a81b8.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "a3eea7578023e4c395e26a1e80f75a93f9e0cdd452f43792e00a79f2a53bdcb1", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a1a57c02b749ff9bdbb53e7c22edf782d6cc8c7a6e2e09024a5d1557ae3d87ef", "generation_seconds_batch": 22.975545894005336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.04180802404880524, "target_z": -0.5390625265945678, "ce": 6.435632705688477, "genuineness": 4.325342178344727, "identity": 0.7083699107170105, "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_Disgust/a3eea7578023e4c395e26a1e80f75a93f9e0cdd452f43792e00a79f2a53bdcb1.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "a464404e8ffd8c4cb69a969470006a2112288ae37f73d9bba9c2084f0fcabbe1", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bdf9c7feb0080cc4ed24bb3254f8243e3b8153a215f25189a48ebb286a67037b", "generation_seconds_batch": 15.30551784299314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26748335361480713, "target_z": 0.09179687974902995, "ce": 6.054384231567383, "genuineness": 4.250029563903809, "identity": 0.6222878694534302, "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_Disgust/a464404e8ffd8c4cb69a969470006a2112288ae37f73d9bba9c2084f0fcabbe1.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "a499ed19bc3737e1ef46321672d92ad53151e076577575054b68cc2247a24908", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b01f49c12b50b84c77c8358c24449f8cec68fb966e693249df8d1e1852cdde3c", "generation_seconds_batch": 19.015857640071772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05011759698390961, "target_z": -0.35156249620077606, "ce": 6.213237762451172, "genuineness": 4.645420074462891, "identity": 0.7653942108154297, "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_Disgust/a499ed19bc3737e1ef46321672d92ad53151e076577575054b68cc2247a24908.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "a49ddd2f8b59b6349a2777082ee593e380ee59201a0ba6d41839b688fcb77e12", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e686ebdbd3c80fc51cd7b2bcce6892689966ccb49f6ec7a061cc480a3691544a", "generation_seconds_batch": 18.861809735069983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055862948298454285, "target_z": -0.33984374430116404, "ce": 6.157639026641846, "genuineness": 4.356721878051758, "identity": 0.6992080807685852, "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_Disgust/a49ddd2f8b59b6349a2777082ee593e380ee59201a0ba6d41839b688fcb77e12.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "a557db534f5e6ee97bd4c137f92ae08dec91551cd08306b742cc95580cbd4739", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce25dcd55ba2e6a520f36bedbaa59d2bdd77e94fd12b89834f3c6778e60015ec", "generation_seconds_batch": 13.745130231021903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12289203703403473, "target_z": -0.20312499240155207, "ce": 5.6254801750183105, "genuineness": 3.9550557136535645, "identity": 0.3997432291507721, "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_Disgust/a557db534f5e6ee97bd4c137f92ae08dec91551cd08306b742cc95580cbd4739.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "a595e2ce5a0f9557afd1fc6471f5e8a2c8647404abb74bdf8989152ce7069733", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "83ed81a2f7c818031f4128aff398b0fcd2520173052f2d6ab51adeed41c98dc0", "generation_seconds_batch": 21.27098125393968, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09225016832351685, "target_z": -0.2656249924015521, "ce": 6.117925643920898, "genuineness": 4.300237655639648, "identity": 0.6917577385902405, "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_Disgust/a595e2ce5a0f9557afd1fc6471f5e8a2c8647404abb74bdf8989152ce7069733.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "a5b0edbfaae618b7115a66f2a90113079bec89c919bd67f577394d5483c864e6", "bucket": "emo_Disgust", "phase": "wording", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f534e398cff6e878a8c00890a2eb95c8070d18990f653ec3953bc4db518df99e", "generation_seconds_batch": 14.419833249063231, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03383910655975342, "target_z": -0.38476561645174606, "ce": 6.348263263702393, "genuineness": 4.143336772918701, "identity": 0.2830807566642761, "hypothesis": "The 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_Disgust/a5b0edbfaae618b7115a66f2a90113079bec89c919bd67f577394d5483c864e6.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "a5c35d284d44781f0fe3b87a00ef2ce99774aa3003b630d9465301310c9406e1", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "22d6fab083b42cee9e8e3f478c78b37aff2efe5dee9fe9cec4b1cf54d502a81b", "generation_seconds_batch": 18.828468912979588, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07597167789936066, "target_z": -0.2988281126525221, "ce": 6.252951145172119, "genuineness": 4.381826400756836, "identity": 0.743632972240448, "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_Disgust/a5c35d284d44781f0fe3b87a00ef2ce99774aa3003b630d9465301310c9406e1.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "a5e2872dcacb0cadaf66c61a6de160e8e7bc76bea903091bd2b7221ba9bbc4a9", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2eef109df181de66a028a1af048f0d1b1d3de3e663280ec9fda40c75546a489c", "generation_seconds_batch": 13.808131155907176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4558134078979492, "target_z": 2.515625174764302, "ce": 6.117925643920898, "genuineness": 3.8169827461242676, "identity": 0.3600703179836273, "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_Disgust/a5e2872dcacb0cadaf66c61a6de160e8e7bc76bea903091bd2b7221ba9bbc4a9.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": "a6ea09abd96e82cd2bf2bfa4858eb4070d08931567cacd1fe2d0fd7eef29b79b", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The road turns left behind the bridge.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5950d9f8b7604e4798d5cf7657ddb93d9cd13559f3fe6b58da99f239f9a30800", "generation_seconds_batch": 15.824438930954784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4963397979736328, "target_z": 0.5585937291042682, "ce": 6.300607204437256, "genuineness": 3.4247303009033203, "identity": 0.4796161651611328, "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_Disgust/a6ea09abd96e82cd2bf2bfa4858eb4070d08931567cacd1fe2d0fd7eef29b79b.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "a759258653e3e7030675837d3d44dff5ef344223b6f9abb71d4552d6d4e536bf", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "50f2c3849201a75cac96a8840eaeb7e293d72b421b0342421cde122afd513a8a", "generation_seconds_batch": 18.88002746796701, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0060699135065078735, "target_z": -0.4414062405019401, "ce": 6.38003396987915, "genuineness": 4.218649387359619, "identity": 0.5180022716522217, "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_Disgust/a759258653e3e7030675837d3d44dff5ef344223b6f9abb71d4552d6d4e536bf.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "a7b19dcb0a513223f653351da2e20df5334aabf5ec11a6752ca3570c17a65328", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f7eb68c8be721bf792fec1eafb682382f03497781f968fd6c1487b143ef12d6f", "generation_seconds_batch": 19.663027686998248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05777806043624878, "target_z": -0.33593750379922394, "ce": 6.157639026641846, "genuineness": 4.356721878051758, "identity": 0.6942962408065796, "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_Disgust/a7b19dcb0a513223f653351da2e20df5334aabf5ec11a6752ca3570c17a65328.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "a7c222ce42a77d23c0b85b651c18693263f685d6c08ea87e3357796fb48dbec7", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd8c7e99f78802e5fb67342749fad1a79938fb0bb46cf0c327d72d4c86b3f23c", "generation_seconds_batch": 18.955616458086297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06065073609352112, "target_z": -0.330078127849418, "ce": 6.221180438995361, "genuineness": 4.369274139404297, "identity": 0.72673100233078, "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_Disgust/a7c222ce42a77d23c0b85b651c18693263f685d6c08ea87e3357796fb48dbec7.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": "a804322bcccbe9e2d823fcfb81db8d636a001396648ac8bc13cc4d5d115d1b98", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e6645c46542d34c5dfc8f3d8581bc084f22a7e2cdedfa79185c0b5fe23b71fd1", "generation_seconds_batch": 13.682532568927854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5860413312911987, "target_z": 2.7812501367720626, "ce": 6.260893821716309, "genuineness": 3.8295347690582275, "identity": 0.4812682867050171, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier, naast de hoge boekenkast. We zetten het naar de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/a804322bcccbe9e2d823fcfb81db8d636a001396648ac8bc13cc4d5d115d1b98.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "a875627fabf1e440397708b7d27f7b1c413f12d87ed63bfd606fe31e54952026", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a9dc3d48df45406efccea1858e0504a0df3e5eaf800d8380eeca1cc82caf62af", "generation_seconds_batch": 18.572296289959922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07501411437988281, "target_z": -0.30078124810038803, "ce": 6.23706579208374, "genuineness": 4.061748504638672, "identity": 0.6463217735290527, "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_Disgust/a875627fabf1e440397708b7d27f7b1c413f12d87ed63bfd606fe31e54952026.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "a875d3c0975ad66b78c77381d15626cf41372063b65ca109967d4d414f0c1c4b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bbb7dc67626b69c9eb35a2fe34a81e1382620a9cd45c7bf25c56d69ec097139e", "generation_seconds_batch": 18.82117853697855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1181042417883873, "target_z": -0.21289062405019402, "ce": 6.229123115539551, "genuineness": 4.344170093536377, "identity": 0.5880751013755798, "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_Disgust/a875d3c0975ad66b78c77381d15626cf41372063b65ca109967d4d414f0c1c4b.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "520a65783414d21672846c4c383418da2460f735521dae1537afd41b17f3d3f1", "generation_seconds_batch": 14.141342513030395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.052990272641181946, "target_z": -0.34570312025097005, "ce": 6.054384231567383, "genuineness": 4.432034492492676, "identity": 0.6126042604446411, "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_Disgust/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "a943c73cab65d6aa75a4eaa9de0d3423514ba8e492ce6e86a47257f00cb359d9", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "eea207047d09ab1b4c650f354b422b20a9f5fa585d5f4b8387ba00923c9f5d76", "generation_seconds_batch": 16.439541931962594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37760257720947266, "target_z": 0.3164062708957318, "ce": 6.1020402908325195, "genuineness": 4.293961524963379, "identity": 0.8734594583511353, "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_Disgust/a943c73cab65d6aa75a4eaa9de0d3423514ba8e492ce6e86a47257f00cb359d9.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "512fbcd61ff659644514442066ffae9ddfb259ec616129a2de517cb69f0c6e70", "generation_seconds_batch": 13.801134734065272, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03383910655975342, "target_z": -0.38476561645174606, "ce": 6.268836498260498, "genuineness": 4.432034492492676, "identity": 0.5775672197341919, "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_Disgust/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "a9b58f8566fcfd6188bf074d65b82e11d6fa8c32ecbf7f2e07a51c389bddcf46", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bc88a65f1edbcf3c49d9ac99a1310c2358c6c6fcdea5ba4bad3967d5a03ea555", "generation_seconds_batch": 18.861148250987753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.014038816094398499, "target_z": -0.482421872150582, "ce": 6.316492557525635, "genuineness": 4.432034492492676, "identity": 0.7412890195846558, "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_Disgust/a9b58f8566fcfd6188bf074d65b82e11d6fa8c32ecbf7f2e07a51c389bddcf46.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "a9e67da01ff059d6b2d782e8d49ab2dbc07d918195626130b79e9cebd03b270f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "951a28acffd38e233d9b39dc74b467544581b44f4873fbde5f95f6945ca8650b", "generation_seconds_batch": 18.868616890977137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1343827247619629, "target_z": -0.17968751899611982, "ce": 6.078212261199951, "genuineness": 3.936227321624756, "identity": 0.33330774307250977, "hypothesis": "The 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_Disgust/a9e67da01ff059d6b2d782e8d49ab2dbc07d918195626130b79e9cebd03b270f.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "a9eecfa0506c00488eee4943278c80f8259eed583e875e458fa083412972cd3c", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "878f48fe8818baf492e8959329ef10ffd572d314cf1c63a8f7219f4d3856248d", "generation_seconds_batch": 19.66788887907751, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0520327091217041, "target_z": -0.34765625569883596, "ce": 5.879645347595215, "genuineness": 4.080576419830322, "identity": 0.40439677238464355, "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_Disgust/a9eecfa0506c00488eee4943278c80f8259eed583e875e458fa083412972cd3c.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "aa2cc4480cadb2ba38958e755413be43ac61ebcf009e72d8314e043509f38209", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d7bfc1d2e49563414cec7e2d6c3ea26ab5dec4dd2c110108004efff8f7b39cb0", "generation_seconds_batch": 19.035920615075156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.103091761469841, "target_z": -0.6640625265945678, "ce": 6.356205940246582, "genuineness": 4.413206577301025, "identity": 0.44990992546081543, "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_Disgust/aa2cc4480cadb2ba38958e755413be43ac61ebcf009e72d8314e043509f38209.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": "aa4c081abad0e69f4b9857e7f0ff3bb3322174adb87fd1139fe69bd03efc4ca1", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e1a320a5780c2bc9d11b3d7902d46d68ab57c85222745b9a84db03d4b4742b33", "generation_seconds_batch": 14.030819098930806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1927938014268875, "target_z": -0.06054686455213411, "ce": 6.141753673553467, "genuineness": 3.948779582977295, "identity": 0.7381977438926697, "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_Disgust/aa4c081abad0e69f4b9857e7f0ff3bb3322174adb87fd1139fe69bd03efc4ca1.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "aaaf0304b3afca9ecdfd1834e28bd265f68751f7d73443ab9ec56ca1cfd7411e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "408e72ec5c16c2623d6107a33c198c2d9c489ed5da2df604b2a0abdd1d8a8f02", "generation_seconds_batch": 20.986065687029622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5135758519172668, "target_z": 0.5937499848031041, "ce": 6.181467056274414, "genuineness": 3.8797430992126465, "identity": 0.6642757654190063, "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_Disgust/aaaf0304b3afca9ecdfd1834e28bd265f68751f7d73443ab9ec56ca1cfd7411e.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "aaafd2e7f82edf1fb7ea6ed74c22c123f4fa7b08855d504c5f45cab2189355c2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "15fa772d4fa39e5ec9a6258579da1848dbccd8933317964813c8ebb8401d15c1", "generation_seconds_batch": 18.932744282996282, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021390840411186218, "target_z": -0.41015625569883596, "ce": 6.173524379730225, "genuineness": 4.607763767242432, "identity": 0.6988486647605896, "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_Disgust/aaafd2e7f82edf1fb7ea6ed74c22c123f4fa7b08855d504c5f45cab2189355c2.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "aaf70a7ae76866b8e46001c428c2b7239e8f8a7df3dcd4b5d431e8dd17cc943b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b522d7f1044b61847021e227bf0ae62b87830e96c0972f58f4264343df79fd41", "generation_seconds_batch": 18.788466191035695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01116614043712616, "target_z": -0.47656249620077606, "ce": 6.205295085906982, "genuineness": 4.406930446624756, "identity": 0.7312119007110596, "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_Disgust/aaf70a7ae76866b8e46001c428c2b7239e8f8a7df3dcd4b5d431e8dd17cc943b.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "001ad243e9b8de91da3ca9c315c28fc5f0fb3136527ee3a44a309da9355c4476", "generation_seconds_batch": 14.203359958017245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05011759698390961, "target_z": -0.35156249620077606, "ce": 6.348263263702393, "genuineness": 4.21237325668335, "identity": 0.41490572690963745, "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_Disgust/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "ab92d85bac57bcb83c78de258af67089bceca295a523297034617c462e1cf5be", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "81d71d5edc15c04bc504641129b081b6eadb804ea486c71f1dc77e95ad061eb1", "generation_seconds_batch": 18.711959389038384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10230452567338943, "target_z": -0.24511719177412697, "ce": 6.0305562019348145, "genuineness": 4.293961524963379, "identity": 0.6670989990234375, "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_Disgust/ab92d85bac57bcb83c78de258af67089bceca295a523297034617c462e1cf5be.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "abaedb3c3e6f2d601d28f37e49e86d8ba4e36c8dfd95fcd9c26910c00f15e0c2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6a9d0c25564773b6e538b7f33ad47e8036b5d0fff092df500f208610b9cdcfc4", "generation_seconds_batch": 18.630437768995762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.058735623955726624, "target_z": -0.3339843683513581, "ce": 6.221180438995361, "genuineness": 4.256305694580078, "identity": 0.5190166234970093, "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_Disgust/abaedb3c3e6f2d601d28f37e49e86d8ba4e36c8dfd95fcd9c26910c00f15e0c2.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "ac5980822d179a7aaa972bfc6a6e5a1bb686048e5a5ced4390d25a15069949e4", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0ad5388a209768817c6100972cdd907711e152863d6407861407c1310090e0db", "generation_seconds_batch": 19.57371441810392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.016911491751670837, "target_z": -0.48828124810038803, "ce": 6.395919322967529, "genuineness": 4.281409740447998, "identity": 0.6719562411308289, "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_Disgust/ac5980822d179a7aaa972bfc6a6e5a1bb686048e5a5ced4390d25a15069949e4.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "ac60cc188e28c3690f496daaea3d484db96666336069d73fb0faed9fa7e70149", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3f421406e251a5cfed4afc0098baa91ff0d019d4b6e8056ff98eac7e6708f306", "generation_seconds_batch": 18.62803293694742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032881543040275574, "target_z": -0.38671875189961197, "ce": 5.7684478759765625, "genuineness": 3.7793264389038086, "identity": 0.6718825101852417, "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_Disgust/ac60cc188e28c3690f496daaea3d484db96666336069d73fb0faed9fa7e70149.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "acad1332251487c4b26eac44b31e5ef8e0afe2ffe176963a6cb1b2826fbd1a46", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "03d8b93bb31a2cf08453cf92bd9eecaa84c69d7f45c389b74c9e119575f4d4be", "generation_seconds_batch": 18.85114219796378, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8464971780776978, "target_z": 3.3125000607875834, "ce": 5.816103935241699, "genuineness": 3.6789097785949707, "identity": 0.597923219203949, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/acad1332251487c4b26eac44b31e5ef8e0afe2ffe176963a6cb1b2826fbd1a46.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "ad1f196de85161c4fcb08e60585a3505ffcea3d67c8888fddbc793d3ab49a2c9", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "caceab1f973568dfbacb200f23a3f0a0454f301b12a715802b488333bf2a187a", "generation_seconds_batch": 19.382100368035026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11235889047384262, "target_z": -0.22460937594980598, "ce": 6.268836498260498, "genuineness": 4.457139015197754, "identity": 0.6446812152862549, "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_Disgust/ad1f196de85161c4fcb08e60585a3505ffcea3d67c8888fddbc793d3ab49a2c9.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "ad8e0eda1da0c1c62d915b5cccd92a365d5018a463fd797fa589dd9a41a54cb3", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cf9af46931e6e05db19f5bdc0b97008b266954ed7eab372cf25f3f28514c5874", "generation_seconds_batch": 18.789595723967068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03989289700984955, "target_z": -0.535156255698836, "ce": 5.772419452667236, "genuineness": 4.545003414154053, "identity": 0.7423336505889893, "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_Disgust/ad8e0eda1da0c1c62d915b5cccd92a365d5018a463fd797fa589dd9a41a54cb3.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "1df1911ae983d17d3da44b2c79e4eb9c01a248b6069339d7ec983f881e583a32", "generation_seconds_batch": 15.042248178040609, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1386917531490326, "target_z": -0.17089842467761912, "ce": 6.221180438995361, "genuineness": 4.256305694580078, "identity": 0.7435946464538574, "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_Disgust/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "adddd173a3c4cb7567e1b78563788d7606605e2acc8e16d68e29f324a6bf1f62", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ca5c232b64c51c0d513bb7ad6e0a0f20e7309c944c84101b1aac58ad8de49d3", "generation_seconds_batch": 19.014376088045537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20045426487922668, "target_z": -0.04492187215058203, "ce": 6.181467056274414, "genuineness": 4.099404335021973, "identity": 0.46590015292167664, "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_Disgust/adddd173a3c4cb7567e1b78563788d7606605e2acc8e16d68e29f324a6bf1f62.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "ade83c0123fa66a019b44739b8d2486ab1ea9adf3c9e09afc946acbac25b81c0", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a47e2640f75f2e178df4130ca8f4cb6d0871b5c1173a13db8232353249ec63da", "generation_seconds_batch": 18.635137372999452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11331644654273987, "target_z": -0.22265625569883593, "ce": 5.959072113037109, "genuineness": 4.036643981933594, "identity": 0.5493769645690918, "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_Disgust/ade83c0123fa66a019b44739b8d2486ab1ea9adf3c9e09afc946acbac25b81c0.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "ae2390294dde1768987e69a81ee2b1d9ee70abfc73ea1aa55ea1424a6ce0308d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0214990be6add84945a10f0b3c57bb6ed6beb1b5904a3ffc434233852dc45c37", "generation_seconds_batch": 21.06154018698726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03096643090248108, "target_z": -0.3906249924015521, "ce": 6.252951145172119, "genuineness": 4.193545341491699, "identity": 0.6419837474822998, "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_Disgust/ae2390294dde1768987e69a81ee2b1d9ee70abfc73ea1aa55ea1424a6ce0308d.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "5ad088d460e7b477320359bb2807c022e08d32c8f9d27324367c90a6f915201f", "generation_seconds_batch": 16.50649294501636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09703795611858368, "target_z": -0.255859375949806, "ce": 6.419747352600098, "genuineness": 4.042920112609863, "identity": 0.29503339529037476, "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_Disgust/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "ae92ade27d3d33acac6e81201d674578e063d76c2df1708f665e26f144f9b8b6", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4b61338757c3566ae58f253a4a24995681b2dceab8eebaf0ce754d898e9a09a1", "generation_seconds_batch": 21.112584298010916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9004294276237488, "target_z": 1.3828124506100885, "ce": 5.6334228515625, "genuineness": 3.8420867919921875, "identity": 0.6123946905136108, "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_Disgust/ae92ade27d3d33acac6e81201d674578e063d76c2df1708f665e26f144f9b8b6.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "aee8de4e9f42af0091f88a1071c67e92fb4bf6ccd9b7acc7f7661706e63d6482", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3df5c56a78ca4dee7f0b94724bf120d6d8c327b8d8eee81f272ee8a2cb01140c", "generation_seconds_batch": 13.685686188051477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01116614043712616, "target_z": -0.47656249620077606, "ce": 6.252951145172119, "genuineness": 4.68307638168335, "identity": 0.808262825012207, "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_Disgust/aee8de4e9f42af0091f88a1071c67e92fb4bf6ccd9b7acc7f7661706e63d6482.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "af92d866f2087ae7aa53edca1543d8d66386e4e1564c3da8f1a8d71240a07969", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4452efd7565638f3434c026f3376086fa809327e1e8773d41c577b8684f3c524", "generation_seconds_batch": 18.77192049100995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07788679003715515, "target_z": -0.294921872150582, "ce": 6.1020402908325195, "genuineness": 4.319066047668457, "identity": 0.7047449350357056, "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_Disgust/af92d866f2087ae7aa53edca1543d8d66386e4e1564c3da8f1a8d71240a07969.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "afceaf855f9a0525571cb47e7da088282cd54f5bbe5e12c0ae4636136c563e7f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ddbbe7230e92c27c5e59806d4d060bf7a8147f74127f191644df8b319e1eff50", "generation_seconds_batch": 16.22194578300696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8774480223655701, "target_z": 1.3359374430116406, "ce": 6.1894097328186035, "genuineness": 4.256305694580078, "identity": 0.5250983834266663, "hypothesis": "Die Tür 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_Disgust/afceaf855f9a0525571cb47e7da088282cd54f5bbe5e12c0ae4636136c563e7f.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "b1330d70f412c45baf3420d52642cacb76a97df0cddc04c84edaa3172292dee7", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8991ad883f478a7c84261f60749672bc6f21cef5dcb9e72199624ac7852fc802", "generation_seconds_batch": 13.801381831988692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0893774926662445, "target_z": -0.2714843683513581, "ce": 6.2767791748046875, "genuineness": 3.8671910762786865, "identity": 0.3410174548625946, "hypothesis": "The 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_Disgust/b1330d70f412c45baf3420d52642cacb76a97df0cddc04c84edaa3172292dee7.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "b138d5b4cd5c6b39a32e6a338f582ff4bf67e9d39d81fcbe492bfcaeb2e2f192", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bfc02147ce4955fc120242088ac7477559acd8a6b57720313428fae5208f5c04", "generation_seconds_batch": 18.837230680976063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21386007964611053, "target_z": -0.017578127849417972, "ce": 6.181467056274414, "genuineness": 3.9425034523010254, "identity": 0.7466481924057007, "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_Disgust/b138d5b4cd5c6b39a32e6a338f582ff4bf67e9d39d81fcbe492bfcaeb2e2f192.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "b13d39be0d1cc0aff2db00232528a7f0bca7180db4dd4eb91bddb0e05fe749df", "bucket": "emo_Disgust", "phase": "wording", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b92b2e76af3b0be0c69d84cc3fc88784152b21dd8462b6db8c88aa72f79d7e30", "generation_seconds_batch": 14.098658032948151, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03797776997089386, "target_z": -0.5312499848031041, "ce": 6.09409761428833, "genuineness": 4.444586753845215, "identity": 0.49151042103767395, "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_Disgust/b13d39be0d1cc0aff2db00232528a7f0bca7180db4dd4eb91bddb0e05fe749df.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "b18c9dd4a2fb065da6f7fe4a4436117e8d697c994153f3c49aa49d3e7691e85d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ac2105f03884b81a6c9983fcbd229750f13f5a21442bd71554e28ddd3a790b85", "generation_seconds_batch": 13.688958378974348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.014996379613876343, "target_z": -0.4843750075984479, "ce": 6.197352409362793, "genuineness": 4.7081804275512695, "identity": 0.5154759883880615, "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_Disgust/b18c9dd4a2fb065da6f7fe4a4436117e8d697c994153f3c49aa49d3e7691e85d.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "b36bce065d0df88ef6003431331c8a2eef1c57b139fa266caa5a9b89969fea33", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1134f3d867919eb1b35fe3efd47dc5a12db1e88f83e613b154c69e1b1fb2dc0d", "generation_seconds_batch": 13.779177353950217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.026178628206253052, "target_z": -0.40039063924708984, "ce": 6.09409761428833, "genuineness": 4.20609712600708, "identity": 0.5078736543655396, "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_Disgust/b36bce065d0df88ef6003431331c8a2eef1c57b139fa266caa5a9b89969fea33.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": "b3e26ffdd0ed1df6d9becafa0b21308fc58bb44aa5263e98f29772130f00b8c2", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "af203bd14962d98ac435d23eaff9f08dfc29fab97497101ddfa1da231d813deb", "generation_seconds_batch": 18.794924393994734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5553994178771973, "target_z": 2.7187500455906877, "ce": 5.6254801750183105, "genuineness": 3.6663577556610107, "identity": 0.599457859992981, "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_Disgust/b3e26ffdd0ed1df6d9becafa0b21308fc58bb44aa5263e98f29772130f00b8c2.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "7d654fdefcf1a9410962f71379dd8bc12b9d8dc7d69b0aaf78f89ec6271f51b6", "generation_seconds_batch": 13.671590057900175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055862948298454285, "target_z": -0.33984374430116404, "ce": 6.38003396987915, "genuineness": 4.293961524963379, "identity": 0.4023633599281311, "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_Disgust/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.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": "b43c2146f8903a178bc5df00a38e6a9c26fda5777f524728da79373c032010fd", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fef045e35f37e9cc642853ae2008a40573af8652e8a87786c0ea2243bcf99ff4", "generation_seconds_batch": 13.682532568927854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.719790458679199, "target_z": 5.093750106378271, "ce": 6.284721851348877, "genuineness": 3.7416701316833496, "identity": 0.42965027689933777, "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_Disgust/b43c2146f8903a178bc5df00a38e6a9c26fda5777f524728da79373c032010fd.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "b45547b1269e8075f71d2185dcc259b64912d1698e18b810817c885bf2f19aa7", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e5db318da9924bec8e0d74fd2257a46f78173acd7785d3918b42cf656d8ed8c6", "generation_seconds_batch": 18.59410536091309, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.06861965358257294, "target_z": -0.5937500151968959, "ce": 6.372091293334961, "genuineness": 4.13078498840332, "identity": 0.6409352421760559, "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_Disgust/b45547b1269e8075f71d2185dcc259b64912d1698e18b810817c885bf2f19aa7.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "b473ab4c3c670266cea8dd4c514b1a6ea2f9055b5ef11431b616356b83c00c8d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4e30656cac9a8b3e5b590b687b5ebc65e6b0a1d85e346ca12bbf2b74c9af5014", "generation_seconds_batch": 15.859796758042648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10852865874767303, "target_z": -0.23242187215058202, "ce": 6.348263263702393, "genuineness": 4.68307638168335, "identity": 0.531757116317749, "hypothesis": "Die Tür 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_Disgust/b473ab4c3c670266cea8dd4c514b1a6ea2f9055b5ef11431b616356b83c00c8d.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "b47cc9415e962128cb0c64de0782c8548a7ee54d26d4fea8a74c77f7b592f66b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0eb27f86fbbbdb14fbf0b8c30ed2872b970f7e624f8e6f2aed515cba00bfdf00", "generation_seconds_batch": 18.503688531927764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.723929762840271, "target_z": 3.0625001823627502, "ce": 6.006728172302246, "genuineness": 3.9173994064331055, "identity": 0.4291338622570038, "hypothesis": "La porte est encore ouverte. J'ai poussé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/b47cc9415e962128cb0c64de0782c8548a7ee54d26d4fea8a74c77f7b592f66b.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": "b47df97cdd1fd412750c6c6584a69d4d81da34793c4d367c3431fe5e83e20aac", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Someone moved the little blue chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6c02e07fc12d446c4899812087c92b008fc8e1ca623d3a186beeb770a166cdae", "generation_seconds_batch": 15.270441215019673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027136191725730896, "target_z": -0.39843750379922394, "ce": 6.340320587158203, "genuineness": 4.024092197418213, "identity": 0.28264763951301575, "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_Disgust/b47df97cdd1fd412750c6c6584a69d4d81da34793c4d367c3431fe5e83e20aac.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "b4a5a999262a05e581eb408a84b0cbf30b16454f05f4326ab21dd35f437588e0", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e7b090e2ac3f8dc297cbd36d2b4abeebadcde2816fed6c547e27f662a46cd5b1", "generation_seconds_batch": 18.84210998599883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.07628010213375092, "target_z": -0.6093749772046563, "ce": 6.4515180587768555, "genuineness": 4.507347106933594, "identity": 0.45765042304992676, "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_Disgust/b4a5a999262a05e581eb408a84b0cbf30b16454f05f4326ab21dd35f437588e0.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "b4a784fb18bef2df5b5a1e3678258294faa667cef7bd2e05052161d664d04716", "bucket": "emo_Disgust", "phase": "wording", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6ccdaabedddba0424559ae8fa8b0e4b9bd7f274a3688f72d37c04d7c98cc2eaa", "generation_seconds_batch": 17.709500534110703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12193447351455688, "target_z": -0.20507812784941798, "ce": 6.38003396987915, "genuineness": 4.68307638168335, "identity": 0.5430426597595215, "hypothesis": "Die Tür 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_Disgust/b4a784fb18bef2df5b5a1e3678258294faa667cef7bd2e05052161d664d04716.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "b4d020bc5e1ece558db56cab2c3062da949ee1b085c869a383d4eb2907b74b7a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "69953943145d226905ff278f2f2b466cdc55ec469d10f27d55a2d3fddbd64075", "generation_seconds_batch": 19.227150340098888, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29237985610961914, "target_z": 0.14257809745562627, "ce": 6.1894097328186035, "genuineness": 4.2374773025512695, "identity": 0.5627181529998779, "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_Disgust/b4d020bc5e1ece558db56cab2c3062da949ee1b085c869a383d4eb2907b74b7a.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "b54d6cf9eb732909282f51a5b56564480553b069ef0c84cd38a5160f6767a7e2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "e83d3aa5409ad304237d2744812e41e169af3af2867707da0c03911f3c3697b9", "generation_seconds_batch": 19.834188638953492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0012821108102798462, "target_z": -0.4511718873474779, "ce": 6.23706579208374, "genuineness": 4.720732688903809, "identity": 0.7984378337860107, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/b54d6cf9eb732909282f51a5b56564480553b069ef0c84cd38a5160f6767a7e2.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "b54f6ba0419bfeedb803f55e1e7a2100b44485abda71cc73989a2d777fe75fc8", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bae3540890f9341cf1e00f5c1570e7373236541fd4bcce232e09ea593c27d02e", "generation_seconds_batch": 18.8949988669483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04532980918884277, "target_z": -0.3613281126525221, "ce": 6.252951145172119, "genuineness": 4.231201171875, "identity": 0.5124373435974121, "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_Disgust/b54f6ba0419bfeedb803f55e1e7a2100b44485abda71cc73989a2d777fe75fc8.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": "b61c7a9a9d6c453ee50d7fbb908af517c2965b05bacafaff5dc3bdfdae99bf32", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f496d9069480067c9fddaa7ff2ebd8ac584986dcc753aa05780a6b907e868f73", "generation_seconds_batch": 14.264559252071194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34887582063674927, "target_z": 0.25781251139767186, "ce": 6.181467056274414, "genuineness": 4.256305694580078, "identity": 0.6280454397201538, "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_Disgust/b61c7a9a9d6c453ee50d7fbb908af517c2965b05bacafaff5dc3bdfdae99bf32.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "b63843428bf8d89eaea96fe0b2a03e2dff14d1c00852aa1e85705d89daac0cc4", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4e2623a06f8e7a5aac2fa20cbc6550582b929347d914f1639df908c8ca9ff410", "generation_seconds_batch": 18.772001510020345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03414754569530487, "target_z": -0.5234375037992239, "ce": 6.197352409362793, "genuineness": 4.494794845581055, "identity": 0.7433513402938843, "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_Disgust/b63843428bf8d89eaea96fe0b2a03e2dff14d1c00852aa1e85705d89daac0cc4.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "b6b2a93a5f0ce3b61770bd26edf35d1f36107f5fc3753e7f59d5aa38f12bc5f0", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "711fc13d4e43eb68b6a47e9126c1177653ea953df116589473fd8b88d053cbc4", "generation_seconds_batch": 21.057148964959197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03414754569530487, "target_z": -0.5234375037992239, "ce": 6.443574905395508, "genuineness": 4.532451152801514, "identity": 0.3729414939880371, "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_Disgust/b6b2a93a5f0ce3b61770bd26edf35d1f36107f5fc3753e7f59d5aa38f12bc5f0.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": "b75ee0a23976c22e4e369e8f286bb0110bc99786e5756f4c7e062dc6c4b59b99", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "13d97a6084400e3982b21ad44c1bd5bbaeb669492e675c6193ddf23bf618dad4", "generation_seconds_batch": 18.54791931307409, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43505609035491943, "target_z": 0.4335937898918516, "ce": 5.967014789581299, "genuineness": 3.835810661315918, "identity": 0.5051642656326294, "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_Disgust/b75ee0a23976c22e4e369e8f286bb0110bc99786e5756f4c7e062dc6c4b59b99.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "b7a65e76ca0296e9e22f5178de0c87de02379c424cd69800c7a13dd8b45d5159", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "46854a178c5cb3ac6ad3200a86153f72846051ea51bfdb3298bd0ab2b381dff3", "generation_seconds_batch": 13.64456719905138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03096643090248108, "target_z": -0.3906249924015521, "ce": 5.780362129211426, "genuineness": 3.6475296020507812, "identity": 0.5939299464225769, "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_Disgust/b7a65e76ca0296e9e22f5178de0c87de02379c424cd69800c7a13dd8b45d5159.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": "b82517e57ddacc90e38aaadd4c80bf532808841c330a81e7830a794d82d1f6ac", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fdf3c10d5ae07659d2e67bdee5a0db6bce0c152b141d4b5038223dea889cb341", "generation_seconds_batch": 13.763904200983234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13342517614364624, "target_z": -0.18164062405019402, "ce": 6.260893821716309, "genuineness": 4.068024158477783, "identity": 0.6220746040344238, "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_Disgust/b82517e57ddacc90e38aaadd4c80bf532808841c330a81e7830a794d82d1f6ac.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "b85286f9d82e2be50f29c881fbaaa43c37fecdb57fec8f58bc7bb6ed8b827927", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aea5096eb2f534b7bb36e0d4586673f41c7f238a2ddd9ee2ffffdb40981661fd", "generation_seconds_batch": 19.637052224949002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29285866022109985, "target_z": 0.14355471077024676, "ce": 6.260893821716309, "genuineness": 4.281409740447998, "identity": 0.7477768659591675, "hypothesis": "Die Tür 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_Disgust/b85286f9d82e2be50f29c881fbaaa43c37fecdb57fec8f58bc7bb6ed8b827927.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "b85acc905a7b1e75244ec298b5d3a2931eb00861ee4f0a90f9545995370c975b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "55adcc5331d39820df518ec4f77f15e30585563af815a63688e5d5ed8b322f32", "generation_seconds_batch": 21.635261405957863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.04180802404880524, "target_z": -0.5390625265945678, "ce": 6.1020402908325195, "genuineness": 4.557555198669434, "identity": 0.7501226663589478, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/b85acc905a7b1e75244ec298b5d3a2931eb00861ee4f0a90f9545995370c975b.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "b865422bb9af3dddbacbcae290d492b549b20bb54e2fb13058468fb1d693b193", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4236813eaf186c4ee4722c08288441382d3211bed69d4b74b0a603d93e27c923", "generation_seconds_batch": 19.188951906980947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30291301012039185, "target_z": 0.16406249620077604, "ce": 6.165581703186035, "genuineness": 4.21237325668335, "identity": 0.4871043562889099, "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_Disgust/b865422bb9af3dddbacbcae290d492b549b20bb54e2fb13058468fb1d693b193.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "b8b7e072a69f4cd71472f55192970ca55445dc08eb4a240f6ba5a8cc9a8597a0", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "14a74305c33e72ec9152c6e51362abb58a184e1e6da2cfad75d0dfc9890a9c73", "generation_seconds_batch": 14.094774086028337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0003245621919631958, "target_z": -0.4531249924015521, "ce": 6.348263263702393, "genuineness": 4.557555198669434, "identity": 0.7327830195426941, "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_Disgust/b8b7e072a69f4cd71472f55192970ca55445dc08eb4a240f6ba5a8cc9a8597a0.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "b9687716d1c95c77d0a192aa49f98bb000d21fc6a181e7cd75a5e01c09756e56", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9a14b31c87e5834fed878684abf666ec7aaa4d78bc46453dc6eee32b13167bc2", "generation_seconds_batch": 18.645328357000835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0268272161483765, "target_z": 1.640625113976719, "ce": 5.704906940460205, "genuineness": 4.143336772918701, "identity": 0.5588940382003784, "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_Disgust/b9687716d1c95c77d0a192aa49f98bb000d21fc6a181e7cd75a5e01c09756e56.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "ba0d51a1434c08e498e8fd64edc1a7195d908516aa2b6ef4606d29121861faab", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "de959f3fd2a5955927d92f589bad2f1d1d12696a97a50fcfb7a40f1b5062336b", "generation_seconds_batch": 13.582637815037742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.172376036643982, "target_z": 1.9375, "ce": 5.5738525390625, "genuineness": 4.118232727050781, "identity": 0.35550570487976074, "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_Disgust/ba0d51a1434c08e498e8fd64edc1a7195d908516aa2b6ef4606d29121861faab.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "012ca6bb0ccf003c381444c485f4226af0356d62121600a5271cc24df07f7ccf", "generation_seconds_batch": 13.664130873978138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01116614043712616, "target_z": -0.47656249620077606, "ce": 6.181467056274414, "genuineness": 4.507347106933594, "identity": 0.6769697070121765, "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_Disgust/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "bb08fd12aead2ba67c2132b1870c5533d5f16e8be874a4b5dfee3da8a07efc8e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ed41942720aee063e43463e3400eae38f38b7be93b6e0919a7141cb8622e0a54", "generation_seconds_batch": 18.789595723967068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.04372312128543854, "target_z": -0.5429687367027162, "ce": 6.109982967376709, "genuineness": 4.331617832183838, "identity": 0.49509960412979126, "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_Disgust/bb08fd12aead2ba67c2132b1870c5533d5f16e8be874a4b5dfee3da8a07efc8e.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "bb5074c0a0accd80ba8135c3f9c7b197c9d5a4ab686c8fbe170e0aad671d1d84", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c066c7114b5c832d11384f2ee907451e8b8c08368e66b8cee106b131f57cb023", "generation_seconds_batch": 16.22194578300696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19566647708415985, "target_z": -0.05468748860232812, "ce": 6.133810997009277, "genuineness": 4.20609712600708, "identity": 0.7419409155845642, "hypothesis": "Die Tür 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_Disgust/bb5074c0a0accd80ba8135c3f9c7b197c9d5a4ab686c8fbe170e0aad671d1d84.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "bbc28b63347156c9378ee06b7e944c72ddab05f6d2e26c8c2e0bd811572e75b7", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dc2b276d1522f404050901ad825f3042f3a016def1f9334977c9b4fd1e6daa2c", "generation_seconds_batch": 18.886185772018507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18992112576961517, "target_z": -0.06640624050194009, "ce": 5.982900142669678, "genuineness": 3.886019229888916, "identity": 0.16162768006324768, "hypothesis": "The 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_Disgust/bbc28b63347156c9378ee06b7e944c72ddab05f6d2e26c8c2e0bd811572e75b7.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "bc3292ff988067398d0beb3f682633f44f36ef857962831bbb3494c4a9ca7b16", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e66ef62d4626e46c9a78aad3fec4d492acb2da91d8812d9a552d0801f69c6f0c", "generation_seconds_batch": 13.83555441396311, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11618912220001221, "target_z": -0.21679687974902995, "ce": 5.95112943649292, "genuineness": 3.9676074981689453, "identity": 0.6432583332061768, "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_Disgust/bc3292ff988067398d0beb3f682633f44f36ef857962831bbb3494c4a9ca7b16.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "bc8f24fa538823213fab2663c43902a0f0eb9924fafa792d5cab11c1353cb9a8", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ea89139ed24e9492cb22ededf975caab4e41fab1e76e8930f077341a0393cfa4", "generation_seconds_batch": 13.813670147908852, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15257634222507477, "target_z": -0.14257812784941798, "ce": 5.982900142669678, "genuineness": 3.6663577556610107, "identity": 0.5976119637489319, "hypothesis": "The 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_Disgust/bc8f24fa538823213fab2663c43902a0f0eb9924fafa792d5cab11c1353cb9a8.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "bcad4215784bb18fe1b1aecc77646759993bae4b0f06a46a0cdff72b7289a09b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "996728a859e1454f2f8ef6a73e69954c59dca59a789fefd2beca5bdc3fefcecc", "generation_seconds_batch": 16.439541931962594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03479665517807007, "target_z": -0.38281251139767186, "ce": 6.133810997009277, "genuineness": 4.406930446624756, "identity": 0.8210330605506897, "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_Disgust/bcad4215784bb18fe1b1aecc77646759993bae4b0f06a46a0cdff72b7289a09b.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "bd104584b3202d3c956b372308c0de27dbd627d2e36320064906bfe26514b9fc", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eceb9dd23a9425bdd165be47bc0bf19446bf6b7c027346e8659b1db0d9d73efa", "generation_seconds_batch": 18.858347604982555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03989289700984955, "target_z": -0.535156255698836, "ce": 6.427689552307129, "genuineness": 4.394378662109375, "identity": 0.5799921154975891, "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_Disgust/bd104584b3202d3c956b372308c0de27dbd627d2e36320064906bfe26514b9fc.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "bd497ed90a06603d59e2d9d6a50d01faf55007f23d5730577c3ab64e3e83db25", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0a6fdaba16211b2ae84c3c98e4a8744ae4252fc32b20b601b6e4d8c91092322f", "generation_seconds_batch": 18.69262325402815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.053947821259498596, "target_z": -0.34375001519689585, "ce": 6.125868320465088, "genuineness": 4.344170093536377, "identity": 0.6605535745620728, "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_Disgust/bd497ed90a06603d59e2d9d6a50d01faf55007f23d5730577c3ab64e3e83db25.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": "bd5a967857608387f706774ad39425404290e370d2d0009000e13c89576f3070", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "90dac01337c9ead612807b0ee95e8fdc84ccf330fa5ef72b3cb694f824c87f2a", "generation_seconds_batch": 14.264559252071194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21577519178390503, "target_z": -0.013671887347477875, "ce": 6.24500846862793, "genuineness": 4.218649387359619, "identity": 0.4584795832633972, "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_Disgust/bd5a967857608387f706774ad39425404290e370d2d0009000e13c89576f3070.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "bd75dacbb39e2cd68f416ff09720207e18c8af0ad099cb972eb4ca0733e33a3e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a9b45ad9dbae1a7839b35232cb07a7dbe0ee2803f6dedd9b25b9e0698783544e", "generation_seconds_batch": 22.226157338009216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27993160486221313, "target_z": 0.11718748860232811, "ce": 6.252951145172119, "genuineness": 4.444586753845215, "identity": 0.46318691968917847, "hypothesis": "Die Tür 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_Disgust/bd75dacbb39e2cd68f416ff09720207e18c8af0ad099cb972eb4ca0733e33a3e.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "bdae4c5b14fa4629694a72c8e83a920c9f37e0b803272e45e3939ba961ac203b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "32d892d7df431eb6a7cebdd72707805ae0101aeef3b6ea9e6d371fd1506fe2aa", "generation_seconds_batch": 18.99569412402343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09895307570695877, "target_z": -0.25195312025097005, "ce": 6.125868320465088, "genuineness": 4.381826400756836, "identity": 0.4711213707923889, "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_Disgust/bdae4c5b14fa4629694a72c8e83a920c9f37e0b803272e45e3939ba961ac203b.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "beb0a585dc59d3d9a4860ff8e6b67392b679a071e35bd6b6293e30f3670f9770", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "18bd5fdd178f1ca35fad5ea113ba6f05b015fb2ef9215cda4f2f0bdc840e0792", "generation_seconds_batch": 19.0818137639435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04916003346443176, "target_z": -0.3535156316486419, "ce": 6.1894097328186035, "genuineness": 4.545003414154053, "identity": 0.7329685091972351, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/beb0a585dc59d3d9a4860ff8e6b67392b679a071e35bd6b6293e30f3670f9770.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "bec4486c4e45fb6b8370640931d36acdfe1ffbd526369678e6234dd434de1109", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3fe92b5a4fcf7a697c452309592c9d5c02aee40f5e293eb48b90e48a6f4d0531", "generation_seconds_batch": 13.754100963007659, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032881543040275574, "target_z": -0.38671875189961197, "ce": 5.816103935241699, "genuineness": 3.9425034523010254, "identity": 0.7462393045425415, "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_Disgust/bec4486c4e45fb6b8370640931d36acdfe1ffbd526369678e6234dd434de1109.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "bec50f815059c597c5ab58db8b370a5676926a34e4b3ee968c0f7320cf89cb80", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e93920d179c92fbb267fd8bfbc77e48abac89c7d3359941b7991a0d37f9b74a9", "generation_seconds_batch": 14.463646415970288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14012807607650757, "target_z": -0.16796876709650782, "ce": 6.1894097328186035, "genuineness": 4.005263805389404, "identity": 0.38105398416519165, "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_Disgust/bec50f815059c597c5ab58db8b370a5676926a34e4b3ee968c0f7320cf89cb80.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "bff0352c7c55819ada7ae387344ea7bfecbce941a918289b2281e94583406e52", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "47c291a48bb79f8aa1266e258a334b2772cd38b62913d2b16b533340f28eba6d", "generation_seconds_batch": 18.88820292800665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12480714917182922, "target_z": -0.19921875189961197, "ce": 6.054384231567383, "genuineness": 3.936227321624756, "identity": 0.4985303282737732, "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_Disgust/bff0352c7c55819ada7ae387344ea7bfecbce941a918289b2281e94583406e52.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "c0673e758dfe267dae85ca4d74a613136018642233e38197df8c4c65a34bac1f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "20601ebc9a148767cc643d6a39daad04527c612c37c016bfe869d6e414f59b5d", "generation_seconds_batch": 13.717075331951492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33594876527786255, "target_z": 0.23144528922975324, "ce": 6.260893821716309, "genuineness": 4.105680465698242, "identity": 0.660851001739502, "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_Disgust/c0673e758dfe267dae85ca4d74a613136018642233e38197df8c4c65a34bac1f.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": "c0931be1e9167ab5eed211dda54712ea6d7c97cc50603240511e18815474632d", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "059933bcd7d9743e92a68d993941c6b0b28bb495e9e32c1885776d4eb57abd0d", "generation_seconds_batch": 13.74690838996321, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2670045793056488, "target_z": 0.09082032722199285, "ce": 6.2767791748046875, "genuineness": 4.005263805389404, "identity": 0.58855140209198, "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_Disgust/c0931be1e9167ab5eed211dda54712ea6d7c97cc50603240511e18815474632d.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": "c0a16e6e179caa70e99d69398010e330d2bdc5816412f35425b6394deb8c8673", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "135687f79a35ae4d460841efcd00231872313c431d4cf56da68286fefc631c32", "generation_seconds_batch": 13.59272231592331, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1324676275253296, "target_z": -0.18359372910426822, "ce": 6.1894097328186035, "genuineness": 3.8169827461242676, "identity": 0.6058316230773926, "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_Disgust/c0a16e6e179caa70e99d69398010e330d2bdc5816412f35425b6394deb8c8673.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "c0da59d25159886eaab98047a692d3b35d1106a465222cc9290a861ee16dddd9", "bucket": "emo_Disgust", "phase": "wording", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a065e718beb2ad3db0ce2fe4b2cb14a722407b675df7d1d4ca14bfcf5ec201fd", "generation_seconds_batch": 14.106234717997722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.04372312128543854, "target_z": -0.5429687367027162, "ce": 6.1894097328186035, "genuineness": 4.419482707977295, "identity": 0.751807689666748, "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_Disgust/c0da59d25159886eaab98047a692d3b35d1106a465222cc9290a861ee16dddd9.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "c18316592f3dabee67e6cc9ea13e37c65e3bca50621a90496f46155cc9095beb", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f50195369a93f8318f0d872df68d4c0415084516fee8c46d73034de26d064c0b", "generation_seconds_batch": 18.851142099010758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03575421869754791, "target_z": -0.380859375949806, "ce": 6.141753673553467, "genuineness": 4.381826400756836, "identity": 0.5749430656433105, "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_Disgust/c18316592f3dabee67e6cc9ea13e37c65e3bca50621a90496f46155cc9095beb.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "c1a69ddc6bbb05d962c570e8d33ed45382c3dd65b76215d636f762e93b09ae32", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2c096dfa7b004b4cee92e727ac4e5f8cb41b93ca599ad13a121497a794f32b61", "generation_seconds_batch": 19.663027686998248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09225016832351685, "target_z": -0.2656249924015521, "ce": 6.24500846862793, "genuineness": 4.595211505889893, "identity": 0.559138298034668, "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_Disgust/c1a69ddc6bbb05d962c570e8d33ed45382c3dd65b76215d636f762e93b09ae32.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "c1cebbbe12b4a6c8741d1ff8213543597c318594e6c3a655694381792d57dac1", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "60f2de0a02e757fb64d0eecca04c83c3b90449057e4ac596d53ebe06225b0fe2", "generation_seconds_batch": 18.933402633061633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07692922651767731, "target_z": -0.2968750075984479, "ce": 6.340320587158203, "genuineness": 4.457139015197754, "identity": 0.6530109643936157, "hypothesis": "Die Tür 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_Disgust/c1cebbbe12b4a6c8741d1ff8213543597c318594e6c3a655694381792d57dac1.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": "c29b949c1fa98a05cfa474663a0a67eefd126c7487243934d13e3cf7b00691df", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "08c7c284fdb80bd11111f29cf516782e3be4e612734a484428a2c54f4359e506", "generation_seconds_batch": 13.74690838996321, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2808891534805298, "target_z": 0.11914059365640232, "ce": 6.181467056274414, "genuineness": 3.7918784618377686, "identity": 0.5741438269615173, "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_Disgust/c29b949c1fa98a05cfa474663a0a67eefd126c7487243934d13e3cf7b00691df.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "c386cb198e3e568ff708bfa4487c9c5c43717d09762d4c754e2902657c2e3cbd", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "64ae3648cbe6fd21b040b6549d012769f4cf77b4b4e8888903e3a19c406c6bd5", "generation_seconds_batch": 14.509159369044937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023305967450141907, "target_z": -0.40624998480310415, "ce": 6.229123115539551, "genuineness": 4.607763767242432, "identity": 0.7650818228721619, "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_Disgust/c386cb198e3e568ff708bfa4487c9c5c43717d09762d4c754e2902657c2e3cbd.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "f13681b5770a5da8cce0f5e9d6720317a56195261c0a505c6e04fb215485eae5", "generation_seconds_batch": 13.733267979929224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024263516068458557, "target_z": -0.40429687974902995, "ce": 6.157639026641846, "genuineness": 4.20609712600708, "identity": 0.5942592024803162, "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_Disgust/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "c47e9492e0dfdbc13419c4ae3fe566cb6e4fc17a09d14cfd6b1fba40eae8f75c", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9603bfd0dbf777fd9ccc2f155228b8d0b8d45f6613454ec89255066d189358a7", "generation_seconds_batch": 18.848381652031094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0035056769847869873, "target_z": -0.46093750379922394, "ce": 6.078212261199951, "genuineness": 4.457139015197754, "identity": 0.6486169099807739, "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_Disgust/c47e9492e0dfdbc13419c4ae3fe566cb6e4fc17a09d14cfd6b1fba40eae8f75c.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "64a98099d0c4cba63181e2559cdfca6702cda07b3cd50643eca723ca523d6253", "generation_seconds_batch": 14.035717035993002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023305967450141907, "target_z": -0.40624998480310415, "ce": 6.149696350097656, "genuineness": 4.306513786315918, "identity": 0.787202775478363, "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_Disgust/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "c4e4e584204d34a578fc9c9811f36c43e4c64da67a25e8e7dac6ed93162eceee", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1c95e31f8c525414e5256a866d3ed28e177fa3733e297ab2273caa5f971c6765", "generation_seconds_batch": 18.8602177829016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7548805475234985, "target_z": 1.0859374430116406, "ce": 5.577824115753174, "genuineness": 3.7542223930358887, "identity": 0.5844728946685791, "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_Disgust/c4e4e584204d34a578fc9c9811f36c43e4c64da67a25e8e7dac6ed93162eceee.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "c5fb7f1b39fff247ff415bb314f3b110b97b1c4fcb769bab91424d423e5a1939", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f046c470efbb49b18b1e25d13f240ba49c256c4c17983687f59c0f2bdbeec779", "generation_seconds_batch": 19.825216441066004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07597167789936066, "target_z": -0.2988281126525221, "ce": 6.046441555023193, "genuineness": 4.306513786315918, "identity": 0.7263126373291016, "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_Disgust/c5fb7f1b39fff247ff415bb314f3b110b97b1c4fcb769bab91424d423e5a1939.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "c6358274a035cf3f9cdd89199f2d1cc037a3fe407b4ba30b0d7d3a99e31ef6dc", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cd6d6af523f3a853d21581681bb5a102ff861df6a0d51e9e758bb8f1d70864f3", "generation_seconds_batch": 18.9378470829688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2090722918510437, "target_z": -0.02734374430116406, "ce": 6.205295085906982, "genuineness": 4.319066047668457, "identity": 0.6627804636955261, "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_Disgust/c6358274a035cf3f9cdd89199f2d1cc037a3fe407b4ba30b0d7d3a99e31ef6dc.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "c680da1eaae655efeb54226189c709a1e1fac78bca0de3d8f5406f3a24859b0f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fe273a7575e90736f9650c5df61c718d4eb48b85084e40c63cfdffe82a5841cb", "generation_seconds_batch": 20.27042346005328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.028402194380760193, "target_z": -0.511718751899612, "ce": 6.372091293334961, "genuineness": 4.406930446624756, "identity": 0.6863740682601929, "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_Disgust/c680da1eaae655efeb54226189c709a1e1fac78bca0de3d8f5406f3a24859b0f.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": "c705dfeed646fda38fbd3f0923ee550cfb17ed48b30e6490b78ed73407f2625f", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a67c0134a77955e82bccefc99c53d15df704772d5c5814cc713c699225bee1b2", "generation_seconds_batch": 13.694621996954083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.321446180343628, "target_z": 4.281250136772063, "ce": 6.284721851348877, "genuineness": 3.6914620399475098, "identity": 0.5359143018722534, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna, naast het raam. Neem ze mee als je hem weggaat.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/c705dfeed646fda38fbd3f0923ee550cfb17ed48b30e6490b78ed73407f2625f.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "c72fdc7622ae527849b15ccff266e609677895fb22a3b29ab9c1c1d8ba3f658d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a3d42824de7bcd97cf9da97b5495810bf7889dd079555ad784dbe1174a6dbc0b", "generation_seconds_batch": 15.911037743091583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05712895095348358, "target_z": -0.5703125113976719, "ce": 6.221180438995361, "genuineness": 4.218649387359619, "identity": 0.41105973720550537, "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_Disgust/c72fdc7622ae527849b15ccff266e609677895fb22a3b29ab9c1c1d8ba3f658d.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "c75dfd757e20dd18ad97e584b315b74494877251b0baa577087b28018e54665d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ed101cb6cdc31dbe7030a6d9986ae1ba36ba4f3f685fc9cb5f811bb64036776a", "generation_seconds_batch": 18.863160587963648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48293399810791016, "target_z": 0.5312500151968959, "ce": 6.23706579208374, "genuineness": 4.105680465698242, "identity": 0.4713342785835266, "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_Disgust/c75dfd757e20dd18ad97e584b315b74494877251b0baa577087b28018e54665d.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "c76982e090eab4eb1359dab21ecaaf48ecb1a947a8db3f7b3173c810981e88f8", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "04770e3bdb325ac8e33218669bd1abc9a21d02927c067ffe349d951a2f2ba0bd", "generation_seconds_batch": 21.750545187969692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26556822657585144, "target_z": 0.08789060885329816, "ce": 6.332377910614014, "genuineness": 4.482243061065674, "identity": 0.6184192895889282, "hypothesis": "Die Tür 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_Disgust/c76982e090eab4eb1359dab21ecaaf48ecb1a947a8db3f7b3173c810981e88f8.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "c779d4f7e9079506ea94fe7191b7ce681d837f7e1b2fe512f648d9dbdcb6c0f6", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e7be0741a8950ef301f12196a4e58ecf30725a52ff1f84985e7483844a1e6510", "generation_seconds_batch": 18.635137372999452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16119436919689178, "target_z": -0.125, "ce": 5.990842819213867, "genuineness": 3.9801597595214844, "identity": 0.6019667387008667, "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_Disgust/c779d4f7e9079506ea94fe7191b7ce681d837f7e1b2fe512f648d9dbdcb6c0f6.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "c7d64e2427dc8069d14c8f9d1c179314a080c53659b6039d8c1e3704172f5d34", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "563df0fda5de4b0f32387b3f9a1c4d25252376752c768411c11181bd7b869183", "generation_seconds_batch": 19.004906325018965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007027462124824524, "target_z": -0.4394531354478659, "ce": 5.919358730316162, "genuineness": 4.18726921081543, "identity": 0.7654229402542114, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/c7d64e2427dc8069d14c8f9d1c179314a080c53659b6039d8c1e3704172f5d34.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "7084273fde86ae96d548c6750454236ac3fc5c7a779f4a3da48f4d38c6bd5c3c", "generation_seconds_batch": 15.042248178040609, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07309900224208832, "target_z": -0.30468748860232814, "ce": 6.197352409362793, "genuineness": 4.344170093536377, "identity": 0.48667261004447937, "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_Disgust/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "c86bda77e8aac318401f0daabe6ac2d7a57a56ac0d947361be52a4048bf06680", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6020c18082f56276ec94e882c98e85d03f403bb4bcbd15b652f6be13d72627d9", "generation_seconds_batch": 18.937570973997936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16406704485416412, "target_z": -0.11914062405019402, "ce": 6.316492557525635, "genuineness": 4.6705241203308105, "identity": 0.5802357196807861, "hypothesis": "Die Tür 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_Disgust/c86bda77e8aac318401f0daabe6ac2d7a57a56ac0d947361be52a4048bf06680.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "c87f2f218b2d17e0030d650394d7933eae54933bba9e359ce32d51f34d4af6eb", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "33e4ad43f0861230092925f61a765338751a9d54adbfb710180dfe43b277af34", "generation_seconds_batch": 18.77635520894546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00733591616153717, "target_z": -0.46875001519689585, "ce": 6.284721851348877, "genuineness": 4.570107460021973, "identity": 0.6519010663032532, "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_Disgust/c87f2f218b2d17e0030d650394d7933eae54933bba9e359ce32d51f34d4af6eb.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": "c88b3b3f512aca470a905c0c0303dce8f743c91a188b58f98369a7cac582f30b", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "08f29cf26ad3bda8f1f20360f8d836f73dbb709f84d472977e067d4f00b8e2a3", "generation_seconds_batch": 18.71268640004564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.019784167408943176, "target_z": -0.494140624050194, "ce": 6.046441555023193, "genuineness": 4.011539936065674, "identity": 0.6513853073120117, "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_Disgust/c88b3b3f512aca470a905c0c0303dce8f743c91a188b58f98369a7cac582f30b.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "5876bc126394113d7d6e0a0dac7b1574dff979ca1efce488cf8850e210ee26db", "generation_seconds_batch": 16.42926665605046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03862689435482025, "target_z": -0.375, "ce": 6.284721851348877, "genuineness": 4.344170093536377, "identity": 0.31254446506500244, "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_Disgust/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.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": "c9143bfb743b1b0afafcd59658f2053c602ff685ff87c1da90929b5d594a87fc", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0e7d3e9c5c309b08b415743272abece1d40671176cf647e06642b405ff6a6141", "generation_seconds_batch": 19.221463984111324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.039584457874298096, "target_z": -0.3730468645521341, "ce": 6.070269584655762, "genuineness": 4.545003414154053, "identity": 0.6260830163955688, "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_Disgust/c9143bfb743b1b0afafcd59658f2053c602ff685ff87c1da90929b5d594a87fc.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": "c999d3b03ebba292633b9b6611d98c0fb71b0e13d7bd502a2189d28e946d073c", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "343e0390bdb15b4d23a6890e0b196ea0fbf9b93d69897201f8ee9fce80da24f5", "generation_seconds_batch": 16.290304147987626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.040542006492614746, "target_z": -0.3710937594980599, "ce": 5.597680568695068, "genuineness": 4.344170093536377, "identity": 0.6254408955574036, "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_Disgust/c999d3b03ebba292633b9b6611d98c0fb71b0e13d7bd502a2189d28e946d073c.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "ca0daa916627c6e076ec3aa118b14966c13ba8a191266e6055aa3aed73548d41", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3c591c95cc533b98bb6ff8759f03fde23f3a42effc92bbd2e88a7c7c685e4d1a", "generation_seconds_batch": 18.76296545402147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1286373734474182, "target_z": -0.19140627089573178, "ce": 6.062326908111572, "genuineness": 3.6789097785949707, "identity": 0.6955957412719727, "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_Disgust/ca0daa916627c6e076ec3aa118b14966c13ba8a191266e6055aa3aed73548d41.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "ca41cbb5d575dd2f9187932b2a7f3fceb3ffff4058b37a84741a2269f7191861", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ccea2d6f081ad8dade420413a6362d252abb54abb27cddf89b85fd584c623903", "generation_seconds_batch": 14.873984358971938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07692922651767731, "target_z": -0.2968750075984479, "ce": 6.268836498260498, "genuineness": 4.7081804275512695, "identity": 0.621590256690979, "hypothesis": "Die Tür 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_Disgust/ca41cbb5d575dd2f9187932b2a7f3fceb3ffff4058b37a84741a2269f7191861.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": "ca6bf8555b39c9fc822f9ccf0db22bee8711925e79271cd9540849dc38c3930b", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "65be1b6d36f9f394dc9efb8e45e2142924d42272f2ff64c167828bd54e7e3983", "generation_seconds_batch": 13.677032361039892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3945295810699463, "target_z": 2.390624992401552, "ce": 6.133810997009277, "genuineness": 3.9676074981689453, "identity": 0.576997697353363, "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_Disgust/ca6bf8555b39c9fc822f9ccf0db22bee8711925e79271cd9540849dc38c3930b.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "cb724e400a7e73725faf8916c686732014054784caa47b67342eba3bb23d424b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "91e445dfcd93c90f314badc5c64e56388d6a4cb9a5ef72a99059da83476c0e5f", "generation_seconds_batch": 18.674954340909608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.402190089225769, "target_z": 2.406250075984479, "ce": 5.02977991104126, "genuineness": 3.587907314300537, "identity": 0.4549506604671478, "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_Disgust/cb724e400a7e73725faf8916c686732014054784caa47b67342eba3bb23d424b.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "cc7c21d2f2bf3e2b6c879d1b064378e71be11bc81ceac2edac7d9588a5d8c309", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b216ce9c65dedaecee8b56badcc604c2c2d43655d834169365a6126dd8f809bd", "generation_seconds_batch": 21.750545187969692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23492637276649475, "target_z": 0.025390639247089855, "ce": 6.23706579208374, "genuineness": 4.507347106933594, "identity": 0.5463886260986328, "hypothesis": "Die Tür 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_Disgust/cc7c21d2f2bf3e2b6c879d1b064378e71be11bc81ceac2edac7d9588a5d8c309.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "cccfb778cf472e0fffa2afccd1866dde65588445c4d0e20f41c705432e05b298", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "ac966461ac7d950ae84496891b3afeee82d8c3dfa1a22044b40d71c1cc583fca", "generation_seconds_batch": 19.022957146982662, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010857701301574707, "target_z": -0.431640624050194, "ce": 6.0305562019348145, "genuineness": 4.18099308013916, "identity": 0.6973758935928345, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/cccfb778cf472e0fffa2afccd1866dde65588445c4d0e20f41c705432e05b298.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": "cd27137e240243e8f2e36ad71aaaffa9058d530347a652f3d79e81595891b26d", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "c8494bb593618e0d725b773f13120a534787d778e629875c9c6dc0317df6e6aa", "generation_seconds_batch": 19.361065022065304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8468061685562134, "target_z": 1.2734374734054323, "ce": 6.23706579208374, "genuineness": 4.068024158477783, "identity": 0.5815605521202087, "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": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/cd27137e240243e8f2e36ad71aaaffa9058d530347a652f3d79e81595891b26d.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "cd9e21977b5d0cd207452ec047b9dbf1c9c51c720b189e0bceffe4214cea64b0", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d5821968aeb004df741f966ba49f4bb319cf36eb293a3a0b6781cc2654b3ed35", "generation_seconds_batch": 18.8991407409776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08841992914676666, "target_z": -0.27343750379922394, "ce": 6.070269584655762, "genuineness": 4.400654315948486, "identity": 0.653942346572876, "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_Disgust/cd9e21977b5d0cd207452ec047b9dbf1c9c51c720b189e0bceffe4214cea64b0.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "cf0f4c1384b8591f1eeecaea44ad0175a1352470501ce5905de00b6cca830895", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "4f14903328341a02355aa5ba0d86f8b153bb3dae072227ed87e4eb4545efea70", "generation_seconds_batch": 13.845715211005881, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.04372312128543854, "target_z": -0.5429687367027162, "ce": 6.348263263702393, "genuineness": 3.961331605911255, "identity": 0.31981194019317627, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/cf0f4c1384b8591f1eeecaea44ad0175a1352470501ce5905de00b6cca830895.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "cf31de9de8a1e8cb6ae45a7d0631070a5e8d5bb3f7bc178e59972879bfff2d4b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "ef804eb003ba18c19f1c502aa64d8e7f50d3136c4c90caaa9f129e4b69e143b3", "generation_seconds_batch": 18.809750888030976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.022656843066215515, "target_z": -0.5, "ce": 6.181467056274414, "genuineness": 3.5973212718963623, "identity": 0.6237667798995972, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/cf31de9de8a1e8cb6ae45a7d0631070a5e8d5bb3f7bc178e59972879bfff2d4b.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "255b11a3a41af8461c4d1f1a36463c5deb19acc212ca3f87a59f4542aad84682", "generation_seconds_batch": 14.044772441033274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04724492132663727, "target_z": -0.357421872150582, "ce": 6.340320587158203, "genuineness": 4.356721878051758, "identity": 0.39984142780303955, "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_Disgust/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "cfbd3173785d4e7cc192053d59da4635c3316bbfc11e0a733f3d9c056d4c9811", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "314dee3e201c181987c05c3d4635cde6fdffef2a7ac01db3096875d8dbb964df", "generation_seconds_batch": 18.72614193696063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.015953928232192993, "target_z": -0.4863281126525221, "ce": 6.24500846862793, "genuineness": 4.582659721374512, "identity": 0.7277598977088928, "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_Disgust/cfbd3173785d4e7cc192053d59da4635c3316bbfc11e0a733f3d9c056d4c9811.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "cfe5837fc182cd316262e9eb98adda3d7b374a9ae46b28ba49a4b64732ab6e3a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "afb03cb9db6ea4831e7bf17089f423d1dd89746608206462a23c53c1cd3d3a86", "generation_seconds_batch": 20.16963824001141, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13725540041923523, "target_z": -0.1738281430463138, "ce": 6.292664527893066, "genuineness": 4.507347106933594, "identity": 0.5303051471710205, "hypothesis": "Die Tür 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_Disgust/cfe5837fc182cd316262e9eb98adda3d7b374a9ae46b28ba49a4b64732ab6e3a.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "cffe4d86bca0fdaec041e3369839fa66edab6bbb95f1e5cfb05da51965a45e9d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1f7c2b8fbe7af80020bf120827981791b96e73bf96fa123495314acee4ac14c8", "generation_seconds_batch": 18.8531412279699, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40824443101882935, "target_z": 0.3789062405019401, "ce": 5.95112943649292, "genuineness": 3.923675537109375, "identity": 0.36208856105804443, "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_Disgust/cffe4d86bca0fdaec041e3369839fa66edab6bbb95f1e5cfb05da51965a45e9d.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "d03a3abbd5fef57abe0f02920d0a45ee8dac7b91ef0fd54857679d8ae4d96427", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "481fd691d020096a9fcfa2986a869e27e09b6254d4ca4fc7347e2059d2e5e421", "generation_seconds_batch": 19.07437884400133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1056559830904007, "target_z": -0.23828124810038803, "ce": 6.109982967376709, "genuineness": 4.268857479095459, "identity": 0.5409178137779236, "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_Disgust/d03a3abbd5fef57abe0f02920d0a45ee8dac7b91ef0fd54857679d8ae4d96427.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "d09689a8a7943bd9dc0aa567c9805ae0065ca3948b9ca004768badf2cb5bd594", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "16584b87187d26ed120aac61d65854b6198db44dee1cb524fa035a143d3b75c7", "generation_seconds_batch": 20.26990204397589, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1678972840309143, "target_z": -0.11132811265252213, "ce": 6.046441555023193, "genuineness": 3.4090399742126465, "identity": 0.46054384112358093, "hypothesis": "The 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_Disgust/d09689a8a7943bd9dc0aa567c9805ae0065ca3948b9ca004768badf2cb5bd594.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "d0c9126f7bd082ee03e7f8b466ae64d08bb3a85fdec9e06fe4d19271ffac8688", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0808f4c4d9848f74e79fba22a4ac5c51b3696001e1e340c1fb1c81f27ffb1c61", "generation_seconds_batch": 18.80373373196926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.07436500489711761, "target_z": -0.6054687670965079, "ce": 6.356205940246582, "genuineness": 4.356721878051758, "identity": 0.27142977714538574, "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_Disgust/d0c9126f7bd082ee03e7f8b466ae64d08bb3a85fdec9e06fe4d19271ffac8688.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "871f0bd622a25ae50a008830caece24bf56993abbcde14129c694edbb043e01e", "generation_seconds_batch": 16.190696337027475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.042457133531570435, "target_z": -0.36718748860232814, "ce": 6.324435234069824, "genuineness": 3.9048471450805664, "identity": 0.49157267808914185, "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_Disgust/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "d17a6c433a57eb8afd2856945bda7c5edbb6caaf25f68316a05d69109f82a44d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2001bc58d466192743793c6a08ebd0296be826321b60e0ca298e05b01837d1df", "generation_seconds_batch": 18.837230680976063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0012821108102798462, "target_z": -0.4511718873474779, "ce": 5.998785495758057, "genuineness": 4.20609712600708, "identity": 0.44497740268707275, "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_Disgust/d17a6c433a57eb8afd2856945bda7c5edbb6caaf25f68316a05d69109f82a44d.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": "d19281ff21297b489e45a7898009827dc434dae1426e6213286e2d18fb2cfb81", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "83bd1faf958710db37b035e40dbc2eb0084e0095987090ab3c9b9c1ed9cede46", "generation_seconds_batch": 13.856822889996693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8311762809753418, "target_z": 3.2812501367720626, "ce": 6.213237762451172, "genuineness": 3.9550557136535645, "identity": 0.6526345014572144, "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": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/d19281ff21297b489e45a7898009827dc434dae1426e6213286e2d18fb2cfb81.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": "d1abb02addb26b0261202d9e9338f7422e42d7e2b0acf98c5ed40b5b04be630d", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "55017373eb91b89c7cf7a816931c1a197d0cabae4a023cfbcbe484bc91748e43", "generation_seconds_batch": 19.221463984111324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.046287357807159424, "target_z": -0.3593750075984479, "ce": 6.173524379730225, "genuineness": 4.293961524963379, "identity": 0.4829480051994324, "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_Disgust/d1abb02addb26b0261202d9e9338f7422e42d7e2b0acf98c5ed40b5b04be630d.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "d1dc01c76ec752d336f136f665ac45c5fe8d40c2a324529a7a4c858de9549fa3", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3a23dc5d1b6bb85ea0b457ac08216e21c0b6f654b9a5836a4190c64ac3a15d2b", "generation_seconds_batch": 14.509159369044937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03671178221702576, "target_z": -0.3789062405019401, "ce": 6.078212261199951, "genuineness": 4.061748504638672, "identity": 0.7571119070053101, "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_Disgust/d1dc01c76ec752d336f136f665ac45c5fe8d40c2a324529a7a4c858de9549fa3.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "d1e1252de180ae47ec7886bb57e509bf067ed907f10c8b3ff929698574d96fac", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f27643138b97159b31853ed48fd0507ad1401a5fe7da2eb8d4108733abfbaf46", "generation_seconds_batch": 18.90036421502009, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009251028299331665, "target_z": -0.47265625569883596, "ce": 6.403861999511719, "genuineness": 4.557555198669434, "identity": 0.512692928314209, "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_Disgust/d1e1252de180ae47ec7886bb57e509bf067ed907f10c8b3ff929698574d96fac.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "cc52332b84c50e8d353104b11cff067bc39f1092862998d6828c6b9b3bc8efec", "generation_seconds_batch": 13.679154508048669, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07309900224208832, "target_z": -0.30468748860232814, "ce": 6.086154937744141, "genuineness": 4.457139015197754, "identity": 0.47462573647499084, "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_Disgust/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.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": "d299eb501de3982962d80cfba614be1d33eadbd13246f8fd296c39b6c76e9ba5", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a2ca798081b7904ff1e2aa04b2c14d569569e81091d3e515f54bd6d3c86173d4", "generation_seconds_batch": 13.575326486025006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20236937701702118, "target_z": -0.041015631648641936, "ce": 6.0146708488464355, "genuineness": 4.042920112609863, "identity": 0.4639158248901367, "hypothesis": "Die Straße führ hinter der Brücke nach links. Geh weiter bis zu dem kleinen Holztor! Ich warte auf der anderen Seite.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/d299eb501de3982962d80cfba614be1d33eadbd13246f8fd296c39b6c76e9ba5.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "d2eac1ce745c0f904e38f9414edf66ac842b95cf62cc2ce754da21fd75cf9dc8", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "79140d63c7644172bcba84dd9e52d1a866a3f016093196b0c9368901210a4af6", "generation_seconds_batch": 19.932317171944305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01786905527114868, "target_z": -0.49023438354825394, "ce": 6.125868320465088, "genuineness": 4.570107460021973, "identity": 0.6426033973693848, "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_Disgust/d2eac1ce745c0f904e38f9414edf66ac842b95cf62cc2ce754da21fd75cf9dc8.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "d32c35c0072e6c65c4815d4151a98f11bb1a0b44f26dc9ab69d1cc5e5ce8289e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8d266cccc1787d8122610d192783f1bfbe8ba15245ad30b506a0511e0d833ed9", "generation_seconds_batch": 22.514783828053623, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07405655086040497, "target_z": -0.30273438354825394, "ce": 6.181467056274414, "genuineness": 3.9550557136535645, "identity": 0.2396971732378006, "hypothesis": "The 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_Disgust/d32c35c0072e6c65c4815d4151a98f11bb1a0b44f26dc9ab69d1cc5e5ce8289e.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "d3d1e3bd1fe14bd28636fe87fba3b86b1062514d407b18d7776197c1dcd74a8f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "687148fc3c542bfe57d687032d501d997911353b170cbb76d8bf39c2ba185141", "generation_seconds_batch": 19.539860747987404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.04180802404880524, "target_z": -0.5390625265945678, "ce": 6.372091293334961, "genuineness": 4.105680465698242, "identity": 0.5290416479110718, "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_Disgust/d3d1e3bd1fe14bd28636fe87fba3b86b1062514d407b18d7776197c1dcd74a8f.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "f9ecf6e1382aff5d81f80ccc1a6c0be80254d26e3e19e8c7deaeab9121697d16", "generation_seconds_batch": 15.35950863105245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021390840411186218, "target_z": -0.41015625569883596, "ce": 5.879645347595215, "genuineness": 4.65797233581543, "identity": 0.653120756149292, "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_Disgust/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "d42f0dd23f305838a8167ed78a860e4d95582108065f63740fb79b7405be31c2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "473a8f0825f32524246815293feedfffd1978e14c569fc1b247fdf8ea7148b4d", "generation_seconds_batch": 18.503688531927764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.46378281712532043, "target_z": 0.49218748860232814, "ce": 5.270045757293701, "genuineness": 3.8044304847717285, "identity": 0.39512401819229126, "hypothesis": "La porte, t'as encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/d42f0dd23f305838a8167ed78a860e4d95582108065f63740fb79b7405be31c2.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": "d4781fdbe643490a2db938ca29ac21978936880381420a4f76e441b3e892520a", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "00d9d2df2d371656e21f21fdbabe6336bd0270aa62664eb97ae50cf549c85873", "generation_seconds_batch": 13.584538255003281, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15832169353961945, "target_z": -0.13085937594980598, "ce": 5.863759994506836, "genuineness": 4.074300289154053, "identity": 0.7483130097389221, "hypothesis": "J'ai secré le numéro sur l'enveloppe. Lis-le bien. Et vérifie les two derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/d4781fdbe643490a2db938ca29ac21978936880381420a4f76e441b3e892520a.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "d4d4cd8fb02010eb3a8b2792f8108052b0937682f29d4c01c91d804482890713", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9aedb0e45dbfa09682ee04e634283195bbc07ca367d43775b4d5ccdcda39e32b", "generation_seconds_batch": 18.893311197985895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13821296393871307, "target_z": -0.17187500759844793, "ce": 6.221180438995361, "genuineness": 4.444586753845215, "identity": 0.6041191220283508, "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_Disgust/d4d4cd8fb02010eb3a8b2792f8108052b0937682f29d4c01c91d804482890713.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "d52b7dadf05f11be87ce0287918070b409688086bc9e52debcf94df44cdc74b1", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "e5e3db3be5fc87b31b2bd5a57dc3178c795cca797881e9b8b54846deb1c15275", "generation_seconds_batch": 22.376564376987517, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.011506199836731, "target_z": 1.6093749468108645, "ce": 6.1894097328186035, "genuineness": 3.6349775791168213, "identity": 0.5123803615570068, "hypothesis": "De deur staat nog open. Ik heb je jas op stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/d52b7dadf05f11be87ce0287918070b409688086bc9e52debcf94df44cdc74b1.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "d6c5b5333785507b3b922872f95cdb5cc9f361999440d6b5c8ef8e696f5b5291", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "74b9737b840e1487bca53b2cab15a38dfb61cebacf2dec6251aff9c92051615e", "generation_seconds_batch": 20.253823427017778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05521382391452789, "target_z": -0.5664062405019401, "ce": 6.41180419921875, "genuineness": 4.281409740447998, "identity": 0.46644940972328186, "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_Disgust/d6c5b5333785507b3b922872f95cdb5cc9f361999440d6b5c8ef8e696f5b5291.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "d71c264337a8e21c15f5f93579f48e341a28b6c84c96c267a730b753d81c83e5", "bucket": "emo_Disgust", "phase": "wording", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3384f5829a81f4b2dcece2926f8242c66b3cb953ceebcc0aad4bd134d7ddaa92", "generation_seconds_batch": 13.933772362070158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.059693172574043274, "target_z": -0.3320312632972839, "ce": 6.133810997009277, "genuineness": 4.507347106933594, "identity": 0.6447558403015137, "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_Disgust/d71c264337a8e21c15f5f93579f48e341a28b6c84c96c267a730b753d81c83e5.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "d72a82086bfdec6c12c9c53a5bae4e7b9c79e1f17bc9cd84429b29a6da80c666", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ea99ddeb01f878588c64079fa62bf6632d1c5c0336630ed700eea8107728f1d4", "generation_seconds_batch": 18.6535364020383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10757109522819519, "target_z": -0.23437500759844793, "ce": 5.974957466125488, "genuineness": 4.482243061065674, "identity": 0.44455331563949585, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/d72a82086bfdec6c12c9c53a5bae4e7b9c79e1f17bc9cd84429b29a6da80c666.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "d756c12f15cd9848b8e5eb34c4676c5c47ea3bec9d6db132dbcadc96b9812385", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "39878b6ef33d5bea05146bf06010a710e073ae197cee4179b919d27190e7f92f", "generation_seconds_batch": 18.68134693603497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04724492132663727, "target_z": -0.357421872150582, "ce": 6.292664527893066, "genuineness": 4.406930446624756, "identity": 0.732795774936676, "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_Disgust/d756c12f15cd9848b8e5eb34c4676c5c47ea3bec9d6db132dbcadc96b9812385.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "d7a04c07433c0f02a9a3402628a57fc38be155b6910c1ec8a0abc3424062335d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9190c497a5abfae846540385ce0a24d5f6e40f29533c137e559ddd01a3cd1d87", "generation_seconds_batch": 18.8172981350217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.005420789122581482, "target_z": -0.46484374430116404, "ce": 6.006728172302246, "genuineness": 4.193545341491699, "identity": 0.7054818868637085, "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_Disgust/d7a04c07433c0f02a9a3402628a57fc38be155b6910c1ec8a0abc3424062335d.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "d8764bd2391ccc7d6ac4e8751d2bcfc5bb53b6a575f6c52f51906dfd26ae819e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c187d640f61978d3bf30fe79f622f2970da69c882c9208d35672a7ff01c60ad0", "generation_seconds_batch": 15.961800151038915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25790777802467346, "target_z": 0.07226564684553778, "ce": 6.046441555023193, "genuineness": 4.193545341491699, "identity": 0.7101001739501953, "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_Disgust/d8764bd2391ccc7d6ac4e8751d2bcfc5bb53b6a575f6c52f51906dfd26ae819e.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "d8863ac19620ee81cc2f39b4a30529dd4e610a1a55966805ccdc15b8ee7150c1", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d1c1aabc7e77e1b790303a1673c0cf0878a4e63fe4b6bef58d72e22c45f25594", "generation_seconds_batch": 13.73438752500806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.09543128311634064, "target_z": -0.6484375037992239, "ce": 6.372091293334961, "genuineness": 4.457139015197754, "identity": 0.2893697917461395, "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_Disgust/d8863ac19620ee81cc2f39b4a30529dd4e610a1a55966805ccdc15b8ee7150c1.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "d8d206748a8982d60e6316ec2450f988b3fb2cc502fc79253f52af5a27798196", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd4174013d59f3952a83e4ffa1d0d4808412e51e2e3f7b517c2e5bf9b05f6395", "generation_seconds_batch": 18.923400352010503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0520327091217041, "target_z": -0.34765625569883596, "ce": 6.173524379730225, "genuineness": 4.080576419830322, "identity": 0.7915594577789307, "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_Disgust/d8d206748a8982d60e6316ec2450f988b3fb2cc502fc79253f52af5a27798196.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": "d99c86aff1dafe691eef196905255c76d125fb5b4bd4a76ea72bdff3ca8cb3c7", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "95b9b30c8ea395f985038f674c0e931c9af4fac2c65728e1604367cdaac505be", "generation_seconds_batch": 13.76190192392096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3105734884738922, "target_z": 0.17968751899611982, "ce": 6.340320587158203, "genuineness": 3.8546390533447266, "identity": 0.54399573802948, "hypothesis": "Je beri kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg naar wanneer we kunnen praten.", "wer": 0.08695652173913043, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/d99c86aff1dafe691eef196905255c76d125fb5b4bd4a76ea72bdff3ca8cb3c7.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "d9e7374744fd3a934e8b96c22b2d3ea36307dae2fe1f2a4ad82985feac98c387", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c55ad41a6961b243d1eb9d15f2e22722bf0b21766deda70cf454133fbf5081e9", "generation_seconds_batch": 19.932317171944305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.04180802404880524, "target_z": -0.5390625265945678, "ce": 6.23706579208374, "genuineness": 4.18099308013916, "identity": 0.6350833177566528, "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_Disgust/d9e7374744fd3a934e8b96c22b2d3ea36307dae2fe1f2a4ad82985feac98c387.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "da04347e3dab2bf671591ff4f259b43f548f868ed93d17565c555c6d7e322d63", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "845665599f3a7179dde3eb3d6b3eef95e9ca712a79825995780fde0aaa6e9b55", "generation_seconds_batch": 13.648610713076778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.014996379613876343, "target_z": -0.4843750075984479, "ce": 6.395919322967529, "genuineness": 4.344170093536377, "identity": 0.650406002998352, "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_Disgust/da04347e3dab2bf671591ff4f259b43f548f868ed93d17565c555c6d7e322d63.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "da7262071fb89e284949f1d990992f27c359ca630714bfb53c1c28458ca4c223", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e259cce2ec8ee9ad6ec50e8f9a0a6fd5b7be650dda218069314f748e610f9cdc", "generation_seconds_batch": 15.669875820050947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03096643090248108, "target_z": -0.3906249924015521, "ce": 6.252951145172119, "genuineness": 4.375550270080566, "identity": 0.5957863330841064, "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_Disgust/da7262071fb89e284949f1d990992f27c359ca630714bfb53c1c28458ca4c223.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "db07dcda6643e3bb19d4ca77478f6c538d1e0ea23887a750df24b828b1e1edcd", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c7ae976189381796138bb3644e33c47b3e07c37c6fb26412b7e9aadf728b8dea", "generation_seconds_batch": 18.76296545402147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14204320311546326, "target_z": -0.16406249620077604, "ce": 6.054384231567383, "genuineness": 3.9550557136535645, "identity": 0.5406904816627502, "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_Disgust/db07dcda6643e3bb19d4ca77478f6c538d1e0ea23887a750df24b828b1e1edcd.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "db187f647432d4549a04356ae7db9c9cf151390d4881c70e7b7abc476232a585", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fcb08d0c0c48f77408450297db71c32066edaac0d7230199e52f3b0fcd559722", "generation_seconds_batch": 18.6349648530595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.593701720237732, "target_z": 2.796874977204656, "ce": 5.700935363769531, "genuineness": 3.4341442584991455, "identity": 0.5182593464851379, "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_Disgust/db187f647432d4549a04356ae7db9c9cf151390d4881c70e7b7abc476232a585.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "8fa8ac919cc2b3f3a791ccfc25f6eb228d119582371f7da6bdb6a2ca75550193", "generation_seconds_batch": 14.203359958017245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07692922651767731, "target_z": -0.2968750075984479, "ce": 6.419747352600098, "genuineness": 4.080576419830322, "identity": 0.3134083151817322, "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_Disgust/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "db3cceb2482044ed3527b589a632fc80927585dd07253331f3ccec11a8e66e44", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b3559f1ef95220a0af07acaa9d113a1bfe1f92620cde296022a8954573c5c6dc", "generation_seconds_batch": 18.851142099010758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03479665517807007, "target_z": -0.38281251139767186, "ce": 6.149696350097656, "genuineness": 4.293961524963379, "identity": 0.5221388339996338, "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_Disgust/db3cceb2482044ed3527b589a632fc80927585dd07253331f3ccec11a8e66e44.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "dbe238b18e6e6b92324e10f8a1bfec3c8bfbb566a7235d4f81843f483a14201c", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4360a66a6305d841ee16ede72787b31c443fb58c901fa49e21e895fe57c3f35c", "generation_seconds_batch": 21.681823451071978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.186090886592865, "target_z": -0.07421875189961198, "ce": 6.229123115539551, "genuineness": 4.049196243286133, "identity": 0.6237066388130188, "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_Disgust/dbe238b18e6e6b92324e10f8a1bfec3c8bfbb566a7235d4f81843f483a14201c.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": "dbf408bfb9d27b258138604e4816d2edb7872d125ec17b9674a29a794cba5e35", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "95d145f069784d27ddb37268a406bc06e070e115e5a7db8744ccdaba883c6936", "generation_seconds_batch": 13.608083826024085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08650481700897217, "target_z": -0.27734374430116404, "ce": 5.895530700683594, "genuineness": 4.099404335021973, "identity": 0.6536371111869812, "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_Disgust/dbf408bfb9d27b258138604e4816d2edb7872d125ec17b9674a29a794cba5e35.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "dc2961b8ff87cd5740c0b2a12ea26bb07a87bb875c668171d245becbfe182456", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f38b2db0a90a1d93459c6646636ff3141b536aefa31518b1371f6fac7eafd3a3", "generation_seconds_batch": 18.630914609064348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.046287357807159424, "target_z": -0.3593750075984479, "ce": 5.879645347595215, "genuineness": 4.300237655639648, "identity": 0.5734750032424927, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschreien.", "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_Disgust/dc2961b8ff87cd5740c0b2a12ea26bb07a87bb875c668171d245becbfe182456.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "dc4af827b216cd5ebb7b9a3da85b1f5fd56a3bf08d79e24c04bcbaf29223ce91", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "8397ab692f0034e65abbf59aaea18cbff21139492b34b415fd91f379289ad74d", "generation_seconds_batch": 18.99189424503129, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03797776997089386, "target_z": -0.5312499848031041, "ce": 6.324435234069824, "genuineness": 3.936227321624756, "identity": 0.47912925481796265, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/dc4af827b216cd5ebb7b9a3da85b1f5fd56a3bf08d79e24c04bcbaf29223ce91.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "dc85af4f74378e9411ef941b929d3f7c3cb365ec53305938c2e62797cfc59122", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4d491e863da3b8b4714833ec7e5e5d43b5c2b2b2f818b30373a5a4f10b33e614", "generation_seconds_batch": 18.8991407409776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1430007517337799, "target_z": -0.16210939114670184, "ce": 6.300607204437256, "genuineness": 4.268857479095459, "identity": 0.7790781259536743, "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_Disgust/dc85af4f74378e9411ef941b929d3f7c3cb365ec53305938c2e62797cfc59122.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "dce9f71ec8319e4e96251dd9fb109da4e7714e7390fcd9d804fe76242d6530f0", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ccfe15f5ffd2e75eaccebf8d6ebc31509cfd48cf0ba2301e159308122fda69d4", "generation_seconds_batch": 18.854214902035892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06256584823131561, "target_z": -0.3261718873474779, "ce": 6.165581703186035, "genuineness": 3.71028995513916, "identity": 0.39334040880203247, "hypothesis": "The 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_Disgust/dce9f71ec8319e4e96251dd9fb109da4e7714e7390fcd9d804fe76242d6530f0.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "dd028d01cd4d279ab6dfbc46e424efee8215b78f506d7698bb5b7c9d822a98e9", "bucket": "emo_Disgust", "phase": "wording", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2d863017d2030b638f1c389fd1636a380f4261db84ed17e0e3d357cfc9418207", "generation_seconds_batch": 14.122584111988544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.059693172574043274, "target_z": -0.3320312632972839, "ce": 6.006728172302246, "genuineness": 4.068024158477783, "identity": 0.5535610914230347, "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_Disgust/dd028d01cd4d279ab6dfbc46e424efee8215b78f506d7698bb5b7c9d822a98e9.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "de0b9c722ef5c7de411d73b30e091791ff1f5193f1f523a396ee2caea187c326", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "758d98f9ab151a4f6c09dcff5aff26f6649a1508f018abbbc788812a9701c9bd", "generation_seconds_batch": 19.990994245978072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15832169353961945, "target_z": -0.13085937594980598, "ce": 6.197352409362793, "genuineness": 4.494794845581055, "identity": 0.5438716411590576, "hypothesis": "Die Tür 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_Disgust/de0b9c722ef5c7de411d73b30e091791ff1f5193f1f523a396ee2caea187c326.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "de2610635916b1fc3e8d54b34c3c0f89f7c66f6faf7c6f4d73f82b252e06e2f5", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2aadfa185542e8529cc17afbdc53ffe074a2a8bcef88b412888eacd503434d77", "generation_seconds_batch": 18.738074940047227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01786905527114868, "target_z": -0.49023438354825394, "ce": 6.316492557525635, "genuineness": 4.595211505889893, "identity": 0.7075411081314087, "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_Disgust/de2610635916b1fc3e8d54b34c3c0f89f7c66f6faf7c6f4d73f82b252e06e2f5.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "def21a5aa2ce7d158d5f9d7d974d945d961570ce2fc84266ecc112a15ed510c6", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "0d27eedb23a038a2d5ef83ea243bdeaeac152b0789928cd47995af316e639534", "generation_seconds_batch": 20.83774839004036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03766933083534241, "target_z": -0.3769531354478659, "ce": 5.2918877601623535, "genuineness": 4.011539936065674, "identity": 0.7020075917243958, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre, nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/def21a5aa2ce7d158d5f9d7d974d945d961570ce2fc84266ecc112a15ed510c6.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "df54cf20b821fe8530bb52d6a00d8bb00ef9bf671654a8278048dbb2f42236d7", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1860f9482f89d07257fe7eb82d5d6dd1ff55163f4f582256064da46f9aa7abcb", "generation_seconds_batch": 15.30551784299314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43122583627700806, "target_z": 0.42578124810038803, "ce": 6.109982967376709, "genuineness": 3.9927117824554443, "identity": 0.7819335460662842, "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_Disgust/df54cf20b821fe8530bb52d6a00d8bb00ef9bf671654a8278048dbb2f42236d7.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "df717da33de162e5927df2c0849b01013a3dc962f487e6d764e58ab316252c12", "bucket": "emo_Disgust", "phase": "wording", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e591958056194cdc5e6654ac95a8cf53fc0a9b36f1c567248a65566966757048", "generation_seconds_batch": 14.419833249063231, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03766933083534241, "target_z": -0.3769531354478659, "ce": 6.252951145172119, "genuineness": 3.9048471450805664, "identity": 0.25341880321502686, "hypothesis": "The 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_Disgust/df717da33de162e5927df2c0849b01013a3dc962f487e6d764e58ab316252c12.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": "df7e54e3a4de51b20ca7835c18067bebd8295f59411adf9afa4279291ae3a86b", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The keys are on the kitchen table.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f530f7850b92560fa9c7b5c065cfe26e02bb6f0382ef57634d7b1822a0eb88ea", "generation_seconds_batch": 18.67156518192496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12384959310293198, "target_z": -0.20117187215058202, "ce": 6.23706579208374, "genuineness": 3.5220088958740234, "identity": 0.4604310393333435, "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_Disgust/df7e54e3a4de51b20ca7835c18067bebd8295f59411adf9afa4279291ae3a86b.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": "dfa5174ae2cfa050911901702bce7a99945e0c347284fa9bd6b78659591f22f3", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Someone moved the little blue chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9aade5889766746317ee60b3e7fcc8177970b24374931489feb6a02d606535dd", "generation_seconds_batch": 13.737125792889856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.043414682149887085, "target_z": -0.36523438354825394, "ce": 6.141753673553467, "genuineness": 3.6663577556610107, "identity": 0.38596391677856445, "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_Disgust/dfa5174ae2cfa050911901702bce7a99945e0c347284fa9bd6b78659591f22f3.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": "dfce40eafb64a264c493271a8e8e96dd10020334a7029a1c4193fcc8fb07aa3d", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "48f992abec4c157977a8cfa5d90e808650319f61b5e641469957c86107e965d5", "generation_seconds_batch": 18.49379915499594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2448415756225586, "target_z": 4.125000273544125, "ce": 6.395919322967529, "genuineness": 3.8546390533447266, "identity": 0.31201040744781494, "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_Disgust/dfce40eafb64a264c493271a8e8e96dd10020334a7029a1c4193fcc8fb07aa3d.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": "e00368b52d914566b394f5ca18a87f6a8effdb77e471fe32f4f2bb1948b2dd51", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I wrote the number on the envelope.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "ecc95274eef5a237da255aad72fa5a073f4620dadef7aaa340d604894cddabb4", "generation_seconds_batch": 18.834865965065546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20619961619377136, "target_z": -0.033203120250970046, "ce": 6.09409761428833, "genuineness": 3.390212059020996, "identity": 0.44642922282218933, "hypothesis": "I wrote the number on the envelope. Read it carefully, and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/e00368b52d914566b394f5ca18a87f6a8effdb77e471fe32f4f2bb1948b2dd51.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": "e01d196e688dc0fcdb2fa227570fa4b1f6bd76cea65b7aff5ae81f8ce018f6bb", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "378eaf8f27180412def409d056521375215c9be5be043489acf4c3ce4a769a2b", "generation_seconds_batch": 13.63742102496326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5442177057266235, "target_z": 0.6562499544093124, "ce": 6.292664527893066, "genuineness": 3.9299514293670654, "identity": 0.7355034351348877, "hypothesis": "Quelqu'un a deplacé la petite chaise bleue. Elle était ici, près de la grand bibliothèque. Nous la remettron après le déjeuner.", "wer": 0.14285714285714285, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/e01d196e688dc0fcdb2fa227570fa4b1f6bd76cea65b7aff5ae81f8ce018f6bb.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "e0471acd31af7bab57b8f6720a834c8bd962c5a6c43197ecf22381c8a67e29a5", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c14fa1eb2313ce412729266caf618f1ea3dde0e4d16981741cba159b508a2f7b", "generation_seconds_batch": 18.78640447196085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.059693172574043274, "target_z": -0.3320312632972839, "ce": 6.2767791748046875, "genuineness": 3.9299514293670654, "identity": 0.300411581993103, "hypothesis": "The 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_Disgust/e0471acd31af7bab57b8f6720a834c8bd962c5a6c43197ecf22381c8a67e29a5.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": "e0b96471a3b6969a09c58131e42ec47041ebc907f4173582619361e4e1b5a274", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Your message arrived after I had left.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3a10f8f32c2461187520ff23ea4cb9868aae11155086aeb18ea2635943d5ffdb", "generation_seconds_batch": 18.888650448061526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12767982482910156, "target_z": -0.19335937594980598, "ce": 5.863759994506836, "genuineness": 3.7542223930358887, "identity": 0.36142754554748535, "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_Disgust/e0b96471a3b6969a09c58131e42ec47041ebc907f4173582619361e4e1b5a274.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": "e179a9518440dd2847ed118d736259b1990eb505f5636e5c72a4d829b4ea7e7b", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I wrote the number on the envelope.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cecb99a36dc857e0ac8a0f2e019c9f377a0ae809b703f804bd27584777fca0cb", "generation_seconds_batch": 18.834865965065546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1305525004863739, "target_z": -0.1875, "ce": 6.221180438995361, "genuineness": 3.355693817138672, "identity": 0.31839942932128906, "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_Disgust/e179a9518440dd2847ed118d736259b1990eb505f5636e5c72a4d829b4ea7e7b.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": "e219815530e5725a2971a0727f3b532d530dac6514bf44a03d8c72c357c32894", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bb5ea12e1bc940c654e8bb8d710600661c1fe35069fc1a92f8d2be1a13518d28", "generation_seconds_batch": 13.619347174069844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.302604079246521, "target_z": 2.203125205158094, "ce": 6.125868320465088, "genuineness": 4.017816066741943, "identity": 0.8225464820861816, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grand 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_Disgust/e219815530e5725a2971a0727f3b532d530dac6514bf44a03d8c72c357c32894.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": "e22cf194cc4d3dfe65ce27082a8562d355cc6cfda013338ae44f483d42f01164", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I wrote the number on the envelope.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "0d7bc9c72b5916b52aa69786113e7dbc1770204e6ad75623fc8379d8240d4e71", "generation_seconds_batch": 15.12154770793859, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07692922651767731, "target_z": -0.2968750075984479, "ce": 6.340320587158203, "genuineness": 3.8546390533447266, "identity": 0.29527372121810913, "hypothesis": "I wrote the number on the envelope. Read it carefully, and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/e22cf194cc4d3dfe65ce27082a8562d355cc6cfda013338ae44f483d42f01164.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": "e244c42b6406b020057671461c42f76d6841adb671f15547104041ef3292d59e", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5491d9bf41579795a962fac1b101909a249d7ac3e9fa25ec723167bc723c13b5", "generation_seconds_batch": 13.653173040947877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03766933083534241, "target_z": -0.3769531354478659, "ce": 6.24500846862793, "genuineness": 4.118232727050781, "identity": 0.6711153984069824, "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_Disgust/e244c42b6406b020057671461c42f76d6841adb671f15547104041ef3292d59e.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "e279a1e3a9cab2bf1950d40892c59c04e89cdcfe87b357337e4a0d5d45440be8", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b87cb8e66b2eb082151ed1811b9fcfc7e4828f5f5ff669b937e21c3a30fc771b", "generation_seconds_batch": 18.769624685985036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03031732141971588, "target_z": -0.5156250227953437, "ce": 6.38797664642334, "genuineness": 4.281409740447998, "identity": 0.47329407930374146, "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_Disgust/e279a1e3a9cab2bf1950d40892c59c04e89cdcfe87b357337e4a0d5d45440be8.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": "e312d204759e3eca6b6212d2e75d1a80eb4d6d7b546909b05c8ccbf3f89a9e5b", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "477d8574463de66533dcfe65abb298c6974815d212b50b0b94bcad23fd3fd7fe", "generation_seconds_batch": 19.308333867928013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2770589292049408, "target_z": 0.11132811265252213, "ce": 6.252951145172119, "genuineness": 4.193545341491699, "identity": 0.5259414315223694, "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_Disgust/e312d204759e3eca6b6212d2e75d1a80eb4d6d7b546909b05c8ccbf3f89a9e5b.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "e3ea5887562ccbb64a38cd533a7ebf7190b334af53ea283aeae44498be0a7328", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "34085537734b943fae1c310c55d94326ce97e6e41e8adf1a8eb71101d2d928e0", "generation_seconds_batch": 18.861809735069983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05107516050338745, "target_z": -0.34960936075291016, "ce": 6.284721851348877, "genuineness": 4.1998209953308105, "identity": 0.6938123106956482, "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_Disgust/e3ea5887562ccbb64a38cd533a7ebf7190b334af53ea283aeae44498be0a7328.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "e43d29799779afba3ecc5ef30f2a4caf60c864d92ba9bee7992bd303952003e1", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "84ba736ac187a08369647d5eadfee223c70a791587f0ca20993ac2937ddeb9ce", "generation_seconds_batch": 16.276912022032775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0520327091217041, "target_z": -0.34765625569883596, "ce": 6.181467056274414, "genuineness": 4.532451152801514, "identity": 0.5518708825111389, "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_Disgust/e43d29799779afba3ecc5ef30f2a4caf60c864d92ba9bee7992bd303952003e1.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "e442bf0af2911ada979f0d4eda541674ce150d9b64b3cc717f7829eb20b3f836", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e7b5a16f05c6abb22ed36febbe9d4a605c613143c182b6eed6046dbe5dd82f8c", "generation_seconds_batch": 13.801381831988692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1985391527414322, "target_z": -0.048828112652522127, "ce": 6.157639026641846, "genuineness": 3.4623863697052, "identity": 0.42157477140426636, "hypothesis": "The 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_Disgust/e442bf0af2911ada979f0d4eda541674ce150d9b64b3cc717f7829eb20b3f836.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "e54410b4c9670813012ee83ed5a83a63f83f89c55f36cfe5dd6e23609a241d53", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6a4e05b6525a8bcb155c2f9f8061e22f975450b2a01d511f612955cfeb3123a7", "generation_seconds_batch": 18.64124210504815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.007366895675659, "target_z": 3.6406248708263855, "ce": 6.221180438995361, "genuineness": 3.8044304847717285, "identity": 0.7341932058334351, "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_Disgust/e54410b4c9670813012ee83ed5a83a63f83f89c55f36cfe5dd6e23609a241d53.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "e55e42bde787b155a2f51bc6547d3194ad18cf70bad6b906f88b704a93d42cff", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6b5a8412e8566e6f7e308e873882859e5694ca75351c749dbe9f6d387631b113", "generation_seconds_batch": 18.837509626057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06831119954586029, "target_z": -0.3144531354478659, "ce": 6.284721851348877, "genuineness": 4.425758361816406, "identity": 0.642078161239624, "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_Disgust/e55e42bde787b155a2f51bc6547d3194ad18cf70bad6b906f88b704a93d42cff.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "e56cb54274c82d104b7cf2014da9ea4fd4c29f9d603e2ad9cf87a44a8ceadcd4", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "974b1fd17fc7319088073a6fdbf9b042e8cc2523ffcc780834eabbd39475d505", "generation_seconds_batch": 19.501534519018605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00733591616153717, "target_z": -0.46875001519689585, "ce": 6.125868320465088, "genuineness": 4.607763767242432, "identity": 0.5843682885169983, "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_Disgust/e56cb54274c82d104b7cf2014da9ea4fd4c29f9d603e2ad9cf87a44a8ceadcd4.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": "e5ca36136c4251814e3b1112dfca2e33d4514f89723600d6344b8d452c0ff152", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "83b3c3c70ec9b34e9287eac197188d2a05a16501929e7fe24c01a655af8708d8", "generation_seconds_batch": 18.636817859951407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3061251640319824, "target_z": 4.2499999696062085, "ce": 6.109982967376709, "genuineness": 3.8420867919921875, "identity": 0.504438042640686, "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_Disgust/e5ca36136c4251814e3b1112dfca2e33d4514f89723600d6344b8d452c0ff152.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "e670ce15290361fe548f0a6b8ec739d126e6c83a1c39c144ff0c843bd3d46ae6", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8c904d495805cb8bf15aeaa7728e375bbd7b5c56dc463604faa1c031374f2e48", "generation_seconds_batch": 18.79905984492507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01756061613559723, "target_z": -0.4179687367027161, "ce": 6.229123115539551, "genuineness": 3.8546390533447266, "identity": 0.5282770991325378, "hypothesis": "The 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_Disgust/e670ce15290361fe548f0a6b8ec739d126e6c83a1c39c144ff0c843bd3d46ae6.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "6e8521cf1a7fa4ed7a8e70ee67303310a3c4e3c9187d0f9370d041505a9400c4", "generation_seconds_batch": 16.42926665605046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055862948298454285, "target_z": -0.33984374430116404, "ce": 6.348263263702393, "genuineness": 4.413206577301025, "identity": 0.49088984727859497, "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_Disgust/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "e7b6781e632d7a5ff45cd79e150a77b1e78d7d532983b131dcf4bcae225ce671", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4a4a46581b52acc67d16ede883b83ccf12b0e32660bae521db9103af3486569b", "generation_seconds_batch": 20.28801999206189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06543852388858795, "target_z": -0.32031251139767186, "ce": 6.173524379730225, "genuineness": 3.7040140628814697, "identity": 0.16453783214092255, "hypothesis": "The 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_Disgust/e7b6781e632d7a5ff45cd79e150a77b1e78d7d532983b131dcf4bcae225ce671.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "e8096449693e0942c35703c90b908f6637f783b46befe8a09bcbc840528eb9ea", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b6e1dbf346fd11f52d8be870f2fa1b7b5cf345bf7c1e87072c23f94b68d945a7", "generation_seconds_batch": 15.10211687698029, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.07053475081920624, "target_z": -0.5976562253050443, "ce": 6.4515180587768555, "genuineness": 4.337893962860107, "identity": 0.5035467147827148, "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_Disgust/e8096449693e0942c35703c90b908f6637f783b46befe8a09bcbc840528eb9ea.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "e825e774178483c7e40995415daad87f41bc23648f56bc1a629f7cccfc0e3108", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5e8b78507e60bfdfe3f95c2d650b1a685bdfc5919a3b2707b8ce2ffa61238608", "generation_seconds_batch": 14.463646415970288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1678972840309143, "target_z": -0.11132811265252213, "ce": 6.149696350097656, "genuineness": 4.124508857727051, "identity": 0.7277274131774902, "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_Disgust/e825e774178483c7e40995415daad87f41bc23648f56bc1a629f7cccfc0e3108.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "e877d908bda4ce182959e6b221444400f66605ea6cd299d1df675ee1142852cb", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c4da95202914ce5fd8d6873e77b0b0c3460ed5b7d4b87871cf68d6b300f5d0ba", "generation_seconds_batch": 13.759320455952547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05011759698390961, "target_z": -0.35156249620077606, "ce": 6.173524379730225, "genuineness": 3.8420867919921875, "identity": 0.49085456132888794, "hypothesis": "The 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_Disgust/e877d908bda4ce182959e6b221444400f66605ea6cd299d1df675ee1142852cb.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "e88383ed164f23cbe7e1bb7709db23f636a2e560d4961412bf5b00face4f95d1", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2c5d9cdc0ceb8a0634858c81657f52ab8b6e6db606f529d69373d8448e00215d", "generation_seconds_batch": 21.099842629977502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08458970487117767, "target_z": -0.28124998480310415, "ce": 6.23706579208374, "genuineness": 4.268857479095459, "identity": 0.663429319858551, "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_Disgust/e88383ed164f23cbe7e1bb7709db23f636a2e560d4961412bf5b00face4f95d1.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "e46982f2a85f7f6fce5605b2922eb222ee31d08edce9edf23fc6c68b2903151a", "generation_seconds_batch": 14.044772441033274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.042457133531570435, "target_z": -0.36718748860232814, "ce": 6.3641486167907715, "genuineness": 4.557555198669434, "identity": 0.5328102111816406, "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_Disgust/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "ea323db9df0782eee522e3154e3297cb3ed5588c5c920c4d4722c3583b053308", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "423a9858c16251315e554188068b21991adc764f7b3332b5325ded65440ecd57", "generation_seconds_batch": 19.00804268300999, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.019784167408943176, "target_z": -0.494140624050194, "ce": 6.23706579208374, "genuineness": 4.645420074462891, "identity": 0.7137027978897095, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/ea323db9df0782eee522e3154e3297cb3ed5588c5c920c4d4722c3583b053308.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": "ea4c115b863bc60de7653430fa7cd96950f23f6b2055183e165c99684d5939a2", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "87c92fb489c58de27f443381fed738731019f7eecd92b9bbf76c8b6e45712570", "generation_seconds_batch": 13.677032361039892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3102644681930542, "target_z": 2.2187500455906877, "ce": 5.919358730316162, "genuineness": 4.030367851257324, "identity": 0.49058428406715393, "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_Disgust/ea4c115b863bc60de7653430fa7cd96950f23f6b2055183e165c99684d5939a2.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "ea8ead06347c92517fe52e9158fdd5703d22c408cf5216baf1e2a75204a660bf", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1ac8116053a928f70c4e557e933203d06734ae3544860b80de3f0b9e02f6cae9", "generation_seconds_batch": 18.674954340909608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.198878526687622, "target_z": 4.0312497720465625, "ce": 5.530168056488037, "genuineness": 3.4812145233154297, "identity": 0.38247033953666687, "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_Disgust/ea8ead06347c92517fe52e9158fdd5703d22c408cf5216baf1e2a75204a660bf.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "ead7682317815e6bd78d984905c066945b8e0632aa5dec46b5f8be020cf13208", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c879035c892aad886d3f824a3a7227dbb727dbd1732045ba174538b118282c60", "generation_seconds_batch": 18.95679457404185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0781952291727066, "target_z": -0.613281248100388, "ce": 6.4515180587768555, "genuineness": 4.582659721374512, "identity": 0.3948359489440918, "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_Disgust/ead7682317815e6bd78d984905c066945b8e0632aa5dec46b5f8be020cf13208.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "ead76d07880385e4b1d8a13473d0d03da866b2214309137ec6f96fbc64dfefe2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "0f02b12de7fe560b574936ee64e7d0ac9c79f6365b241790b5b9103dc716e753", "generation_seconds_batch": 19.078272970044054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06160829961299896, "target_z": -0.3281249924015521, "ce": 6.213237762451172, "genuineness": 4.105680465698242, "identity": 0.6927838921546936, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/ead76d07880385e4b1d8a13473d0d03da866b2214309137ec6f96fbc64dfefe2.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "eaefeefb2ef1c41bc9718077992e277157d6d77fb12440236685b7f3ca6aa5da", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "b572a9ba1af61a97e89964bdf78d9918a3ca8ed6b3316c7e2db00098bd07e5fa", "generation_seconds_batch": 13.820246979012154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3086583614349365, "target_z": 0.17578124810038803, "ce": 6.205295085906982, "genuineness": 3.7165660858154297, "identity": 0.6377936601638794, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/eaefeefb2ef1c41bc9718077992e277157d6d77fb12440236685b7f3ca6aa5da.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": "eb02f56b75fef1cb0e05803e3e14146c51daf0c449223979e6754cfcc865ba04", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "855629641d876c94cecaa52fdb8f88c1ee218cbf5e04f24adea619e107816d8b", "generation_seconds_batch": 13.613788124057464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08554725348949432, "target_z": -0.27929687974902995, "ce": 6.324435234069824, "genuineness": 3.9927117824554443, "identity": 0.7244060039520264, "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_Disgust/eb02f56b75fef1cb0e05803e3e14146c51daf0c449223979e6754cfcc865ba04.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "ebd6274cc25c970768e09dabce65ec98b1b203e253d74636920192c00079aacd", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b2c738ce554682dc12700d1c66c2ada8e753bb0c76840cc01c900058b433e645", "generation_seconds_batch": 15.859796758042648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10852865874767303, "target_z": -0.23242187215058202, "ce": 6.316492557525635, "genuineness": 4.796044826507568, "identity": 0.6112772822380066, "hypothesis": "Die Tür 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_Disgust/ebd6274cc25c970768e09dabce65ec98b1b203e253d74636920192c00079aacd.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "f62bd6380802dfde51814d00c4816acfabbcc83696d8304cba8d4d810d85fa24", "generation_seconds_batch": 13.692619667970575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.053947821259498596, "target_z": -0.34375001519689585, "ce": 6.125868320465088, "genuineness": 4.532451152801514, "identity": 0.7383712530136108, "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_Disgust/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "ee894bb465281e19bb2281c07e4112a7158139228db69caa2292f17b01ded6db", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "07565f773bc1d29a86a6133c0d4ee3514d943274750c62bce186f1a9a927ce59", "generation_seconds_batch": 13.73438752500806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.09160105884075165, "target_z": -0.6406250227953437, "ce": 6.348263263702393, "genuineness": 4.469690799713135, "identity": 0.45015639066696167, "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_Disgust/ee894bb465281e19bb2281c07e4112a7158139228db69caa2292f17b01ded6db.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": "eeac86276570ccbe16b0fbca7e0978fce9d0d390d55ddbbf1b657e5e4573067f", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "2683dba9919e65b1d8505bfca635ede20bc6475a98a8d83b540b87cc287f46fd", "generation_seconds_batch": 14.220813627936877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07309900224208832, "target_z": -0.30468748860232814, "ce": 6.1020402908325195, "genuineness": 4.494794845581055, "identity": 0.6390341520309448, "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": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/eeac86276570ccbe16b0fbca7e0978fce9d0d390d55ddbbf1b657e5e4573067f.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "ef099c905e411e927d7f84da1d3479c44a99d44c7a993f409872c6cda60ba722", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b70cc2df6e19c418deeed9f2ffce9afde27d9e3a16459bab2bfe94e23e10116a", "generation_seconds_batch": 19.601622223039158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0044632405042648315, "target_z": -0.46289063924708984, "ce": 6.149696350097656, "genuineness": 4.7332844734191895, "identity": 0.5035249590873718, "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_Disgust/ef099c905e411e927d7f84da1d3479c44a99d44c7a993f409872c6cda60ba722.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": "ef8651a71545874ad717c8a6445efe4365de7e649ab45d69cf1ab225c13c9249", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "d53d0d24d48eecc3ac3895bc4405262d534411c8e4344ff85e68f0651f8d383b", "generation_seconds_batch": 18.794924393994734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41877758502960205, "target_z": 0.40039063924708984, "ce": 6.078212261199951, "genuineness": 3.8420867919921875, "identity": 0.580211341381073, "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": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/ef8651a71545874ad717c8a6445efe4365de7e649ab45d69cf1ab225c13c9249.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": "ef92492202faf2b64d5e50171cf314db65c39ab056a1f76c459bf5dfce48d377", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1e1a0ce382ec1b8935574f9b86dc336135bf6a3ab43aa474e107383354290651", "generation_seconds_batch": 18.769895566045307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7625410556793213, "target_z": 1.1015625265945677, "ce": 5.609594821929932, "genuineness": 3.8546390533447266, "identity": 0.6311980485916138, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reben 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_Disgust/ef92492202faf2b64d5e50171cf314db65c39ab056a1f76c459bf5dfce48d377.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": "efb7ed68bf7da7f56379b78e242509374bee2f17448136dfc972d4ea201eb25f", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "65bae69b9ff60c11d27ae2135d4d06405f9d63aa69e5e50d92b0806a85703b85", "generation_seconds_batch": 18.769895566045307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6763607859611511, "target_z": 0.925781248100388, "ce": 4.927517890930176, "genuineness": 3.8044304847717285, "identity": 0.5657550692558289, "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_Disgust/efb7ed68bf7da7f56379b78e242509374bee2f17448136dfc972d4ea201eb25f.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "efb7f546893192aa0cc1429bfd0e1f9e8062a2dc71eeb3e08cf69e8b8650b8fe", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0a40b17db78066f23688c96af817e053b435a9652a374f2ad52b0e117c087c7f", "generation_seconds_batch": 19.080667793983594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05712895095348358, "target_z": -0.5703125113976719, "ce": 6.260893821716309, "genuineness": 4.331617832183838, "identity": 0.29416385293006897, "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_Disgust/efb7f546893192aa0cc1429bfd0e1f9e8062a2dc71eeb3e08cf69e8b8650b8fe.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "f007e1c35dc009cb02a1c611cd804c06edec72113420f215b5d4d3f67deafa59", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1b41639b303cbdf65f56b1fe88a798c5c60973dd200355399be67708ec9a068d", "generation_seconds_batch": 22.376564376987517, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7044694423675537, "target_z": 5.062499939212417, "ce": 6.205295085906982, "genuineness": 3.6098732948303223, "identity": 0.5678073167800903, "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_Disgust/f007e1c35dc009cb02a1c611cd804c06edec72113420f215b5d4d3f67deafa59.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "f03a89440138720cd7a7805fb8412c7cf925b04c5544785ab4428a939ea12c75", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a204e67df4dd6c540ce56730ec5e02b855488256517d645029a027e619273141", "generation_seconds_batch": 21.655973118031397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2234356701374054, "target_z": 0.001953135447865894, "ce": 5.919358730316162, "genuineness": 4.243753433227539, "identity": 0.741614043712616, "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_Disgust/f03a89440138720cd7a7805fb8412c7cf925b04c5544785ab4428a939ea12c75.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "f0681633994008b741f7f7a7144a138bcb45a97349a65efaa34aefb1e39962a7", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "2eaa37db157093f677653f2eafa6472b527721932ae6517131428ac748ad3082", "generation_seconds_batch": 15.749064119998366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08650481700897217, "target_z": -0.27734374430116404, "ce": 6.252951145172119, "genuineness": 4.1998209953308105, "identity": 0.644327700138092, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/f0681633994008b741f7f7a7144a138bcb45a97349a65efaa34aefb1e39962a7.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "f0f4c89caf2b5aef6a980f98eed1e50e90111f649b1841d117790c1357428fe7", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "84d9cb32f2d901e3aac00660e19d7617ecc291994ed905a97966ae66c2da459a", "generation_seconds_batch": 14.82676362991333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06926876306533813, "target_z": -0.3125, "ce": 6.24500846862793, "genuineness": 4.7081804275512695, "identity": 0.8690689206123352, "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_Disgust/f0f4c89caf2b5aef6a980f98eed1e50e90111f649b1841d117790c1357428fe7.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "f17003c2e2d3b9e45efd234fe31832996ee6101ff1b8856446cfd508b5b56912", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bbd9f2770692888d848e01099e9581905ab8c48785be2e8254f1d778bd9fb54d", "generation_seconds_batch": 18.745470514986664, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7740316987037659, "target_z": 1.1249999088186249, "ce": 6.141753673553467, "genuineness": 4.005263805389404, "identity": 0.3918588161468506, "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_Disgust/f17003c2e2d3b9e45efd234fe31832996ee6101ff1b8856446cfd508b5b56912.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "f175b99228c16f3178e834b922681e7e71f31ed5cd67a8ab7e53bc38766b577c", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0fe6d1d185f0e7fee04513a762589b2e643455edafecbffb775e10cb1d1310df", "generation_seconds_batch": 18.921585524920374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09225016832351685, "target_z": -0.2656249924015521, "ce": 6.133810997009277, "genuineness": 4.281409740447998, "identity": 0.5307761430740356, "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_Disgust/f175b99228c16f3178e834b922681e7e71f31ed5cd67a8ab7e53bc38766b577c.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "f17ad4e327a0d0662fa3406c9d68274dc95e6d20e68984d11b82fca100159a36", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8d535cc65db4f769146b3b7f9e84fb95fc9e47c2c1293dcbe548abf70834fa46", "generation_seconds_batch": 18.809353880002163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007027462124824524, "target_z": -0.4394531354478659, "ce": 6.197352409362793, "genuineness": 4.482243061065674, "identity": 0.6088523268699646, "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_Disgust/f17ad4e327a0d0662fa3406c9d68274dc95e6d20e68984d11b82fca100159a36.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "f1b387fc96e4ff77735c95eff4ff1f144a685369d69355660de216ea46f04d96", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "80a711b5c248347488f3a49825624cdd4a88bead310e67eb0eafd57a0ff49656", "generation_seconds_batch": 18.48711035505403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5400785207748413, "target_z": 2.687500121575167, "ce": 5.967014789581299, "genuineness": 4.055472373962402, "identity": 0.6761408448219299, "hypothesis": "La porte t'est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Donc.", "wer": 0.1111111111111111, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/f1b387fc96e4ff77735c95eff4ff1f144a685369d69355660de216ea46f04d96.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "f1d982640c225d2372423cc7bdf31705b8855ac14448f9a9fb16b9c1fb4bc9bf", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3ec0c94b03f99891e00f82f58ef34e498a49c7734c3ef16c155e86ad0fd73314", "generation_seconds_batch": 18.919475527014583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.08585570752620697, "target_z": -0.6289062708957318, "ce": 6.459460258483887, "genuineness": 4.394378662109375, "identity": 0.39126116037368774, "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_Disgust/f1d982640c225d2372423cc7bdf31705b8855ac14448f9a9fb16b9c1fb4bc9bf.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "83475af1f62885bcd98ab646305f2ce36815d8508ca02dcfbbbf27e81af31e26", "generation_seconds_batch": 13.801134734065272, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023305967450141907, "target_z": -0.40624998480310415, "ce": 6.173524379730225, "genuineness": 4.632867813110352, "identity": 0.6059447526931763, "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_Disgust/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.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": "f25e260024f95ff6b77bf2e46eb902703600aa2b6df0ee7266bbbbdd594f4b0e", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "abaafe56dde5ce8b4154e35def4ade96163aac7ad594e0d79c66456cedf03291", "generation_seconds_batch": 18.638177991029806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.030348300933838, "target_z": 3.687499878424833, "ce": 5.5659098625183105, "genuineness": 3.722842216491699, "identity": 0.7026987075805664, "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_Disgust/f25e260024f95ff6b77bf2e46eb902703600aa2b6df0ee7266bbbbdd594f4b0e.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "f286616c9ee808025a56e57c99c0dca21cb8d952847794a8377c49e7d9eaba3c", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bd66637379aee6369023f13232d097250301fe162b7f29b3c1b44dfc50d79e1e", "generation_seconds_batch": 18.962981618009508, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11235889047384262, "target_z": -0.22460937594980598, "ce": 6.070269584655762, "genuineness": 4.118232727050781, "identity": 0.6410976052284241, "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_Disgust/f286616c9ee808025a56e57c99c0dca21cb8d952847794a8377c49e7d9eaba3c.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "f2a8e437d9b0e235cd3e9fc39012b0a3e4512d8201bf35baf4a08add7ede26ee", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4d5a5c0c101018e48dff70576578ca3741ccace3ab23825007493aa44a05685e", "generation_seconds_batch": 22.661220000009052, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.047553375363349915, "target_z": -0.5507812784941797, "ce": 6.316492557525635, "genuineness": 4.256305694580078, "identity": 0.5345275402069092, "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_Disgust/f2a8e437d9b0e235cd3e9fc39012b0a3e4512d8201bf35baf4a08add7ede26ee.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "f2ac88f90426bd6fd82a8aabcc5274e6b281c1505dd0e5541524bb7d6da3bfba", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f54717732549a51dc81b22e940672a6dbd4fa921da789e20fd22be70afe6e174", "generation_seconds_batch": 18.869263818953186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01116614043712616, "target_z": -0.47656249620077606, "ce": 6.475345611572266, "genuineness": 4.293961524963379, "identity": 0.5928010940551758, "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_Disgust/f2ac88f90426bd6fd82a8aabcc5274e6b281c1505dd0e5541524bb7d6da3bfba.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "f31a3329bc6c450bda6ac2a45a762203796b3613e551143343c442dd8a3c0768", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f816eade79620744a9e5a9cd188fddd64c48afd126c8af710ff1f05abffb1dd6", "generation_seconds_batch": 18.97944925702177, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17076995968818665, "target_z": -0.10546873670271613, "ce": 5.796247482299805, "genuineness": 4.2249250411987305, "identity": 0.7091061472892761, "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_Disgust/f31a3329bc6c450bda6ac2a45a762203796b3613e551143343c442dd8a3c0768.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "f3e2885b8effe954d0644b6e1f47ab0869548dea921357b8e5d3281c482c4664", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4cebd69331b0318b9c9e56399ecbf3b20e5938a185b945d5364c1151c07b58df", "generation_seconds_batch": 18.711451445007697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.078844353556633, "target_z": -0.2929687367027161, "ce": 6.324435234069824, "genuineness": 4.632867813110352, "identity": 0.6740161180496216, "hypothesis": "Die Tür 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_Disgust/f3e2885b8effe954d0644b6e1f47ab0869548dea921357b8e5d3281c482c4664.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "f3e73f89a694d2c1e9fdea32eb4eda5f1efbf887b907f9d6d930044c38023468", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3d9f5360d389708f495f4ca2a73f7c9af8e56d272676777d1d6e6a64fabc09ea", "generation_seconds_batch": 18.572296289959922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03192397952079773, "target_z": -0.3886718873474779, "ce": 5.6413655281066895, "genuineness": 4.068024158477783, "identity": 0.4144327640533447, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinab...", "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_Disgust/f3e73f89a694d2c1e9fdea32eb4eda5f1efbf887b907f9d6d930044c38023468.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "f451aff8446c7f9e5005e593e8d282056273a464082bf45affac24516a378e43", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f2cb21b0f2fa638b6683fd44654cb0ace82f38252005f51349ee25ee8751ac0b", "generation_seconds_batch": 14.838319631991908, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09991063177585602, "target_z": -0.25, "ce": 6.173524379730225, "genuineness": 4.074300289154053, "identity": 0.5394191145896912, "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_Disgust/f451aff8446c7f9e5005e593e8d282056273a464082bf45affac24516a378e43.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "f4625e3809974c1f51fb0525c5157aa98415314ce52d02d28693244e24a07bd0", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "14631be25d08640410de7039fcc4a518fec3b0b971849afc5ed35b19227cd8ac", "generation_seconds_batch": 14.689833348034881, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8506364226341248, "target_z": 1.2812500151968957, "ce": 6.2767791748046875, "genuineness": 4.143336772918701, "identity": 0.39885687828063965, "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_Disgust/f4625e3809974c1f51fb0525c5157aa98415314ce52d02d28693244e24a07bd0.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "f46572004c67422946591efe80832abaa65eeeba9629df91a7e2ebf92c37ae38", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "733ab12dcb3165ce5c90bf1d3723b5cd247c065ea3de41fcc3ae2d3700ca5804", "generation_seconds_batch": 18.868616890977137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03766933083534241, "target_z": -0.3769531354478659, "ce": 6.205295085906982, "genuineness": 4.18099308013916, "identity": 0.33465760946273804, "hypothesis": "The 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_Disgust/f46572004c67422946591efe80832abaa65eeeba9629df91a7e2ebf92c37ae38.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "f4706505857b6025bf570fcc3fdb103c7d95349452d2762f474baff6fd50c0e6", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "028571a6fd00ed62816e11746c6137bab74167e9408191738d1de0ad688e60fe", "generation_seconds_batch": 19.022957146982662, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12289203703403473, "target_z": -0.20312499240155207, "ce": 6.24500846862793, "genuineness": 4.162164688110352, "identity": 0.6794193387031555, "hypothesis": "I don't think she trouved the petite boîte. Elle était près de la vieille fenêtre. We've regarded ensemble what it contiens.", "wer": 0.631578947368421, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/f4706505857b6025bf570fcc3fdb103c7d95349452d2762f474baff6fd50c0e6.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "f4c6ca692326847bf342e28c1f670722a997fa03c8878fba651a89ef010b552f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "219d139ef9225755fbfc878504efe95d87e4bcb22513d48457c7083b87cda6b0", "generation_seconds_batch": 18.788483090000227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.053947821259498596, "target_z": -0.34375001519689585, "ce": 6.3641486167907715, "genuineness": 4.796044826507568, "identity": 0.773743212223053, "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_Disgust/f4c6ca692326847bf342e28c1f670722a997fa03c8878fba651a89ef010b552f.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": "f4f7a0e5665798c4ea7c30f082b6e35c76c4943cc0934b217d9dcde27b8f2944", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "dd4935471c993d8942c5fa9862ee66f202f1c0ed3d7cc48da5116ebaadc437d7", "generation_seconds_batch": 13.785327820922248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.900120496749878, "target_z": 3.4218751595674064, "ce": 6.070269584655762, "genuineness": 4.011539936065674, "identity": 0.49856340885162354, "hypothesis": "Die Schlüsse liegen auf dem Küchentisch. Ich suchte in der Schublade dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.047619047619047616, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/f4f7a0e5665798c4ea7c30f082b6e35c76c4943cc0934b217d9dcde27b8f2944.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "f516155ed3e5b7df0cda00007a7af3a59f898eca3aef623cd6539aa4da0653d7", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6057934a8db7bb04853dba1606b139777b9de9fca0e8b43cc1aca0b35f3a0dc0", "generation_seconds_batch": 22.647154180915095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08363214135169983, "target_z": -0.28320312025097005, "ce": 6.213237762451172, "genuineness": 4.268857479095459, "identity": 0.5315809845924377, "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_Disgust/f516155ed3e5b7df0cda00007a7af3a59f898eca3aef623cd6539aa4da0653d7.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "f5197846a52432b5a04abda69be7b886fa68feb61c173af64de4f9cbfb054c27", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d23d24161b41bb7ca934606c00e689a67b811bda27e089729eb254d705b93cc1", "generation_seconds_batch": 21.09830873494502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07309900224208832, "target_z": -0.30468748860232814, "ce": 6.3641486167907715, "genuineness": 4.300237655639648, "identity": 0.5935543775558472, "hypothesis": "Die Tür 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_Disgust/f5197846a52432b5a04abda69be7b886fa68feb61c173af64de4f9cbfb054c27.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "f5310ab44210f20aef0664d4f20ee9d42241b5424bf4733f5ad2de08e2afbfad", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e7c28594d28210a6192517df6d05abb91b569b1f2d44c7d8c9b9d3ee17b79fbf", "generation_seconds_batch": 18.682836029911414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09799551218748093, "target_z": -0.25390625569883596, "ce": 6.197352409362793, "genuineness": 4.268857479095459, "identity": 0.6080285906791687, "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_Disgust/f5310ab44210f20aef0664d4f20ee9d42241b5424bf4733f5ad2de08e2afbfad.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "f5630ed4791bde81dc4c78f836d6aa0a3ebf090925b3b8b9a46a624abbabfab2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4bd5db81600d01d89d0b843f6be177a4b0397240623aacbfaad6dccc5b5138ec", "generation_seconds_batch": 15.327921935007907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1099649965763092, "target_z": -0.22949218417567904, "ce": 6.133810997009277, "genuineness": 4.400654315948486, "identity": 0.5304564237594604, "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_Disgust/f5630ed4791bde81dc4c78f836d6aa0a3ebf090925b3b8b9a46a624abbabfab2.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-0", "key": "f5bcce9ed17135ddd3eb84eaaf464f3ff55ccf2b7a4cb65a9c1e6aa49c78cdc5", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2e1441d41ea6f0dea0831ef098bc1e05ca4caa239c16455016a40e547f8686af", "generation_seconds_batch": 21.76520595198963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07597167789936066, "target_z": -0.2988281126525221, "ce": 6.197352409362793, "genuineness": 4.3127899169921875, "identity": 0.7800387144088745, "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_Disgust/f5bcce9ed17135ddd3eb84eaaf464f3ff55ccf2b7a4cb65a9c1e6aa49c78cdc5.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "f5beb93dddf05a9cc959276bc5989743acd157b91f0202259a6e18bf01630a75", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a56c182e2a78d6db760181d9532b402b12431bef169a32e7a9b6bf48335c9a50", "generation_seconds_batch": 18.861148250987753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04437224566936493, "target_z": -0.36328124810038803, "ce": 6.2767791748046875, "genuineness": 4.632867813110352, "identity": 0.6106996536254883, "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_Disgust/f5beb93dddf05a9cc959276bc5989743acd157b91f0202259a6e18bf01630a75.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": "f5c3a02da0b10f1f4bb79f1ece414bf7b8ba194fbf96b37d34368ea06c5cd8ec", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "b0ffc7c89a443cb44e965954bba9bf81d46fe9eb5afbdf3c3168887c6dee6382", "generation_seconds_batch": 13.635724282939918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09703795611858368, "target_z": -0.255859375949806, "ce": 6.308549880981445, "genuineness": 4.074300289154053, "identity": 0.6549266576766968, "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": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/f5c3a02da0b10f1f4bb79f1ece414bf7b8ba194fbf96b37d34368ea06c5cd8ec.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "f5c54c0156be0c1a3c16078a1e2de1c4a1c40dabf96855b6c39195b32f7a7d4e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "00de2c342b5df873b253f63f3bd079faa507879a86cffe7d76b5329d21335dfa", "generation_seconds_batch": 13.813670147908852, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34265169501304626, "target_z": 0.2451172069710228, "ce": 6.046441555023193, "genuineness": 3.525146961212158, "identity": 0.1302873194217682, "hypothesis": "The 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_Disgust/f5c54c0156be0c1a3c16078a1e2de1c4a1c40dabf96855b6c39195b32f7a7d4e.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "f6ad54ea98540e5f8d3700052e95d701ddaf755ea59c3efd3975716d2f71fc9c", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "ae50941a68c441a02c92e3498f446e6793fb82609698f9d509af8453090e6b07", "generation_seconds_batch": 22.378481727093458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0035056769847869873, "target_z": -0.46093750379922394, "ce": 6.316492557525635, "genuineness": 4.494794845581055, "identity": 0.6013896465301514, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/f6ad54ea98540e5f8d3700052e95d701ddaf755ea59c3efd3975716d2f71fc9c.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": "f6c67a2cef4814dfa80162649f089189ebb69efd1c3cc21508021cca1e8bd2f6", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Someone moved the little blue chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "b1fdfc36a8374dc2d490c3e95ba3807a7d1fe4dfebfb9dc464ef09efb7bdf8bf", "generation_seconds_batch": 18.843967269989662, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.042457133531570435, "target_z": -0.36718748860232814, "ce": 6.221180438995361, "genuineness": 3.798154592514038, "identity": 0.3394031822681427, "hypothesis": "Someone moved the little blue chair. It used to stand here, beside the tall bookshelf. We can put it back after lunch.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/f6c67a2cef4814dfa80162649f089189ebb69efd1c3cc21508021cca1e8bd2f6.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "f729863cf148a5fbf6020ce6733e8c94289de526f6192e016e424290111d1e78", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "53155c60813bcf230e91e88cd8a727c8d5b7e721d31207eb33ad9ee5eba85a2b", "generation_seconds_batch": 14.12661617307458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09512284398078918, "target_z": -0.25976561645174606, "ce": 6.070269584655762, "genuineness": 4.796044826507568, "identity": 0.6734120845794678, "hypothesis": "Die Tür 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_Disgust/f729863cf148a5fbf6020ce6733e8c94289de526f6192e016e424290111d1e78.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "6ab5f321c8e4af94dc25c53c8eb0240528d944d15922dd966dcc4b497537f7b9", "generation_seconds_batch": 13.664130873978138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.026487082242965698, "target_z": -0.5078125113976719, "ce": 6.062326908111572, "genuineness": 4.532451152801514, "identity": 0.7589095830917358, "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_Disgust/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "f7d5fdf0f04d7cde8953891dfe212275fd1a85ca1df4e74b62adcbaf9a6b6e91", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "853e045dc8269048302f30a9bc33b3431659b1376b696d2ee549895892896b8d", "generation_seconds_batch": 21.112584298010916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.996185302734375, "target_z": 1.5781250227953438, "ce": 5.792276382446289, "genuineness": 3.9801597595214844, "identity": 0.6438226103782654, "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_Disgust/f7d5fdf0f04d7cde8953891dfe212275fd1a85ca1df4e74b62adcbaf9a6b6e91.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_Disgust", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": "043cd4aceb02f1fa76cdec301e14fccb452e0d7a340a7203159976a62fb37206", "generation_seconds_batch": 13.69517502200324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0006330013275146484, "target_z": -0.455078127849418, "ce": 6.3641486167907715, "genuineness": 4.557555198669434, "identity": 0.5564178228378296, "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_Disgust/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "f8dec459ce874db1738b1352e7f898425882c55d461cc989d1f6f8d81787f578", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6367f498a8d42c7bd3c5a497daa8fdf39d6afbe48a871f85cb562cb4b45d640d", "generation_seconds_batch": 14.133002788992599, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09991063177585602, "target_z": -0.25, "ce": 6.197352409362793, "genuineness": 4.017816066741943, "identity": 0.48192429542541504, "hypothesis": "The 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_Disgust/f8dec459ce874db1738b1352e7f898425882c55d461cc989d1f6f8d81787f578.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": "f8df9998300fb32c61bfc82694d4a46f76032ec68c2186b3c0508f200518842b", "bucket": "emo_Disgust", "phase": "heldout", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The keys are on the kitchen table.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "5bfbe819212f9c1e5e438b9ca766d705de3d9ab986b720f4848fb7c84222fe00", "generation_seconds_batch": 15.1254305629991, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10182575136423111, "target_z": -0.24609374430116407, "ce": 5.998785495758057, "genuineness": 3.660081624984741, "identity": 0.39997366070747375, "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": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/f8df9998300fb32c61bfc82694d4a46f76032ec68c2186b3c0508f200518842b.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "f8f00df92b027d2c247474e812c458f7769ac8eca3dda842207ce2841384eefb", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "ee9e8c02bc2ea52eac5431682a8f3a620df90307de2eea03da2409d2607f2420", "generation_seconds_batch": 13.779177353950217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.016911491751670837, "target_z": -0.48828124810038803, "ce": 6.24500846862793, "genuineness": 4.494794845581055, "identity": 0.7690975069999695, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/f8f00df92b027d2c247474e812c458f7769ac8eca3dda842207ce2841384eefb.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "f914d3531ad9cc90cc9b87688036f48a33482d6db65bed4339cf0cdafece25a9", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5b8abbaea34770a10ff085061311e548e6dcd94a25108307c633836752899e15", "generation_seconds_batch": 21.94266980199609, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05490538477897644, "target_z": -0.34179687974902995, "ce": 6.332377910614014, "genuineness": 4.444586753845215, "identity": 0.6809716820716858, "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_Disgust/f914d3531ad9cc90cc9b87688036f48a33482d6db65bed4339cf0cdafece25a9.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "f99c2c834fb7a4dab5cb72c63326571ccf7e76e0262efa45cb3e2fcb981907af", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "163607798903bb521a05fd7eaee9c6fae47770a8758aed94ebd53390a5a98b8c", "generation_seconds_batch": 13.84536940290127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09991063177585602, "target_z": -0.25, "ce": 6.157639026641846, "genuineness": 3.7165660858154297, "identity": 0.334237664937973, "hypothesis": "The 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_Disgust/f99c2c834fb7a4dab5cb72c63326571ccf7e76e0262efa45cb3e2fcb981907af.mp3" }, { "id": "emo_Disgust-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_Disgust-es-1", "key": "f9a70fe02a30ac7957c6c5c94e69062c83fce733c82f7afaf09be4e3e1bc6571", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ac787d18549268cb81710480c77522e8f60328cabb51332a3bf96a983d8aa937", "generation_seconds_batch": 20.39458282000851, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.045638248324394226, "target_z": -0.5468750075984479, "ce": 6.157639026641846, "genuineness": 4.68307638168335, "identity": 0.6649284362792969, "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_Disgust/f9a70fe02a30ac7957c6c5c94e69062c83fce733c82f7afaf09be4e3e1bc6571.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "fa06bfadace1082e5e28bb2553278b3b0870dbe77a6273b91838dc27dd24cad4", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "d7178546d424340ffd4a9737bbdf538987ef9cf7a63f6128f0d35b45032b48eb", "generation_seconds_batch": 22.760368408053182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17076995968818665, "target_z": -0.10546873670271613, "ce": 6.078212261199951, "genuineness": 4.036643981933594, "identity": 0.31459128856658936, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disgust/fa06bfadace1082e5e28bb2553278b3b0870dbe77a6273b91838dc27dd24cad4.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "fa14d6b37a0d53555315a2044b9874a2f6e81ae0af5af5ada61dfed8ec7279c2", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c7cd4b6a949227cd5406e34de3f39114d3e1805baef04a794ccb0574d9222281", "generation_seconds_batch": 18.87537111598067, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009900137782096863, "target_z": -0.4335937594980599, "ce": 6.300607204437256, "genuineness": 3.9299514293670654, "identity": 0.41034960746765137, "hypothesis": "The 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_Disgust/fa14d6b37a0d53555315a2044b9874a2f6e81ae0af5af5ada61dfed8ec7279c2.mp3" }, { "id": "emo_Disgust-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_Disgust-en-1", "key": "fa5827c3ef2a862efa9edf7fc3cff0558190d1aeed9fdff0a127bd1dd930ee8a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8100034519d9ea022460ebd7423547393949688e2f048c7236f086479c2706a2", "generation_seconds_batch": 19.080667793983594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.06095917522907257, "target_z": -0.5781249924015521, "ce": 6.332377910614014, "genuineness": 4.124508857727051, "identity": 0.4790118932723999, "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_Disgust/fa5827c3ef2a862efa9edf7fc3cff0558190d1aeed9fdff0a127bd1dd930ee8a.mp3" }, { "id": "emo_Disgust-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_Disgust-es-0", "key": "fa584036e9eb7c668e6c7b11fd322613b78555c163a479ba950df81ebcac2c16", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bca7c83899406afa3c7b6e4dbfa7fd2b0311e52b9705397cca36f1e73fdc7f3e", "generation_seconds_batch": 13.764533638954163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2183388471603394, "target_z": 2.0312500151968957, "ce": 6.070269584655762, "genuineness": 3.7542223930358887, "identity": 0.5503714084625244, "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_Disgust/fa584036e9eb7c668e6c7b11fd322613b78555c163a479ba950df81ebcac2c16.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "fadc01f72a2c5fab6c8dbf20131eb3423665881d65cd1e368e3c3e3e7ecf6cb1", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2930200218fa253c0fdf06f1baee6ca17cadebae23e058e26340a53205d862cb", "generation_seconds_batch": 18.788648099056445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4072868824005127, "target_z": 0.3769531354478659, "ce": 6.252951145172119, "genuineness": 4.005263805389404, "identity": 0.8527896404266357, "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_Disgust/fadc01f72a2c5fab6c8dbf20131eb3423665881d65cd1e368e3c3e3e7ecf6cb1.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-1", "key": "fb2206f5876b3d8381e705e6dee5e544508e336af241d101b4e6bce4b29a576b", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "729f207b8e16497bcca5e036d6e85a6eabb684f25069453053ba51b52da29e8f", "generation_seconds_batch": 13.88762010994833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30291301012039185, "target_z": 0.16406249620077604, "ce": 6.332377910614014, "genuineness": 4.13078498840332, "identity": 0.5214319229125977, "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_Disgust/fb2206f5876b3d8381e705e6dee5e544508e336af241d101b4e6bce4b29a576b.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "fb501b94aadbe80ed4b15aed48853b0f6a1a3fab1fdffb98d8007e519157ce9e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8f85957d73aabe2c5185d33a70ba57ce8c8af6688d9b1f545400c757ac74e15c", "generation_seconds_batch": 13.759320455952547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.042457133531570435, "target_z": -0.36718748860232814, "ce": 6.1894097328186035, "genuineness": 3.961331605911255, "identity": 0.18845590949058533, "hypothesis": "The 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_Disgust/fb501b94aadbe80ed4b15aed48853b0f6a1a3fab1fdffb98d8007e519157ce9e.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "fbbfe41b32af30ca9ccb6b61728b8f8c5d6d8958109546597cd8d34fe4426cef", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ef91ac9a651b7173ce069ed803387538d5c1092782b5c012bb57dba244fa9178", "generation_seconds_batch": 18.963250042055734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08075946569442749, "target_z": -0.28906249620077606, "ce": 6.046441555023193, "genuineness": 4.105680465698242, "identity": 0.2027810513973236, "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_Disgust/fbbfe41b32af30ca9ccb6b61728b8f8c5d6d8958109546597cd8d34fe4426cef.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "fbe17adabf83f30e5363aabe2f9daf9f1efed7f0a45bbcb2660704a843fb7614", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "729d3c61ca51632c595d6dd9f44ffe6a095797a1ac36293af35f48d15fa677cf", "generation_seconds_batch": 19.539860747987404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.022656843066215515, "target_z": -0.5, "ce": 6.348263263702393, "genuineness": 4.319066047668457, "identity": 0.6881937384605408, "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_Disgust/fbe17adabf83f30e5363aabe2f9daf9f1efed7f0a45bbcb2660704a843fb7614.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "fc0678f60225026e0347510f3431298fb76371ed51f83f1e69e6850fb14ffc4a", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "41c965ba7188c7837547edd5bcb0b734e9e248bde3e08c5afd54077fec3b65a6", "generation_seconds_batch": 18.77927955100313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4120746850967407, "target_z": 0.3867187822934037, "ce": 5.95112943649292, "genuineness": 4.362998008728027, "identity": 0.2711353302001953, "hypothesis": "Die Tür 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_Disgust/fc0678f60225026e0347510f3431298fb76371ed51f83f1e69e6850fb14ffc4a.mp3" }, { "id": "emo_Disgust-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_Disgust-en-0", "key": "fcb7506b7ac4bfe623a4d220e5496b4fce16a7e7166c6f621abab86f3f6a6063", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a4f7bc9f8c91def23f9a2b4d8e8e04312dcbd4d29b1f37eca08b346c1ba05786", "generation_seconds_batch": 18.859989639022388, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14395831525325775, "target_z": -0.16015625569883593, "ce": 6.308549880981445, "genuineness": 3.8671910762786865, "identity": 0.48409196734428406, "hypothesis": "The 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_Disgust/fcb7506b7ac4bfe623a4d220e5496b4fce16a7e7166c6f621abab86f3f6a6063.mp3" }, { "id": "emo_Disgust-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_Disgust-nl-0", "key": "fd2eddef17ff5e98a6afd05eb1171e4ceaa1f5d015bd0495a80454bf3e71621e", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "214c4807e8e1b4871e75764f36fef4da6a24f7747c15bf0bfe0c902577263fd4", "generation_seconds_batch": 21.104080714052543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1181042417883873, "target_z": -0.21289062405019402, "ce": 6.268836498260498, "genuineness": 4.105680465698242, "identity": 0.6594607830047607, "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_Disgust/fd2eddef17ff5e98a6afd05eb1171e4ceaa1f5d015bd0495a80454bf3e71621e.mp3" }, { "id": "emo_Disgust-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_Disgust-fr-1", "key": "fd462291e475febdb014cf5c12abbff3ee50627b257e260c988704f880459ed8", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6d1130e7863ac968bd5c1bb952a603e7fc5159c0f7a7368800578f985a94ebf4", "generation_seconds_batch": 18.62803293694742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7893526554107666, "target_z": 1.1562499544093126, "ce": 5.816103935241699, "genuineness": 3.71028995513916, "identity": 0.7949790954589844, "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_Disgust/fd462291e475febdb014cf5c12abbff3ee50627b257e260c988704f880459ed8.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "feff2b74dc22a1623919424321050e1056ee0d965bf7e0023699edd70d01e99f", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6fc209532dac56c40b5cb05ab8f896a542d0ff99bbd6fe86930a518cc25007c6", "generation_seconds_batch": 18.83880132099148, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05490538477897644, "target_z": -0.34179687974902995, "ce": 6.205295085906982, "genuineness": 4.432034492492676, "identity": 0.5462262630462646, "hypothesis": "Die Tür 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_Disgust/feff2b74dc22a1623919424321050e1056ee0d965bf7e0023699edd70d01e99f.mp3" }, { "id": "emo_Disgust-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_Disgust-de-1", "key": "ff289bbc6f9cc1e19716e5651439044904d0049ad45c65589522903fbfde4985", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8e507c380b70039f952329425f91b0e0d4bae943e606338f8d2fc86437586275", "generation_seconds_batch": 18.804265890968964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12193447351455688, "target_z": -0.20507812784941798, "ce": 5.998785495758057, "genuineness": 4.042920112609863, "identity": 0.24049240350723267, "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_Disgust/ff289bbc6f9cc1e19716e5651439044904d0049ad45c65589522903fbfde4985.mp3" }, { "id": "emo_Disgust-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_Disgust-de-0", "key": "ffee4c142ba32144fa12c927deb9823b8dcae8846d93ee3ae9f77b980827664d", "bucket": "emo_Disgust", "phase": "grid", "candidate": "manual-981ced9f650c", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(A visceral feeling of revulsion; recoiling emphasis, tense consonants and an unmistakably repelled tone. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f63009350f911821879fc795ec2640a0e150dbf189765e86a6ee7eed1246d7d4", "generation_seconds_batch": 18.83880132099148, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0663960874080658, "target_z": -0.318359375949806, "ce": 6.181467056274414, "genuineness": 4.607763767242432, "identity": 0.5941786766052246, "hypothesis": "Die Tür 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_Disgust/ffee4c142ba32144fa12c927deb9823b8dcae8846d93ee3ae9f77b980827664d.mp3" }, { "key": "original-emo_Disgust-de-0-seed1701-scale0.0", "bucket": "emo_Disgust", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "68d224277a972eb02478a4af4a7dc62478809c7fab552c76887fbda8c5f23e50", "task_id": "emo_Disgust-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05777806043624878, "target_z": -0.33593750379922394, "ce": 6.109982967376709, "genuineness": 4.444586753845215, "identity": 0.5436921715736389, "hypothesis": "Die Tür 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_Disgust/de/7cf7564bcd64b0a3d3de0907.mp3" }, { "key": "original-emo_Disgust-de-0-seed1701-scale0.5", "bucket": "emo_Disgust", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "4b450114a31116e7c8e1c87f10999843c4a46f798597094a7550dfe6b1e71dfd", "task_id": "emo_Disgust-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09033504128456116, "target_z": -0.2695312632972839, "ce": 6.1894097328186035, "genuineness": 4.532451152801514, "identity": 0.5718284845352173, "hypothesis": "Die Tür 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_Disgust/de/95249fc4ed4380047721c5af.mp3" }, { "key": "original-emo_Disgust-de-0-seed1701-scale0.75", "bucket": "emo_Disgust", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "6274a897485541b7ef3ab1fcd155a1c792c57c67d48811097b8ba29c94d701a9", "task_id": "emo_Disgust-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04916003346443176, "target_z": -0.3535156316486419, "ce": 6.173524379730225, "genuineness": 4.632867813110352, "identity": 0.5261877179145813, "hypothesis": "Die Tür 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_Disgust/de/d219fc2c36c1674ff780b127.mp3" }, { "key": "original-emo_Disgust-de-0-seed1701-scale1.0", "bucket": "emo_Disgust", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "2d48bdefb652450edd5272ff616df2f310b65f1504aaa8964fb49790094176df", "task_id": "emo_Disgust-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07501411437988281, "target_z": -0.30078124810038803, "ce": 6.292664527893066, "genuineness": 4.65797233581543, "identity": 0.6156188249588013, "hypothesis": "Die Tür 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_Disgust/de/197adc501ab641f52b9002a7.mp3" }, { "key": "original-emo_Disgust-de-0-seed1702-scale0.0", "bucket": "emo_Disgust", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "7abf15286db39663ec956e47c4b5a1a4c26fcdbf714f4d4075aaf8c4a22a2d71", "task_id": "emo_Disgust-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06735365092754364, "target_z": -0.3164062405019401, "ce": 6.109982967376709, "genuineness": 4.444586753845215, "identity": 0.6662576198577881, "hypothesis": "Die Tür 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_Disgust/de/2724b53b58b4118960caa225.mp3" }, { "key": "original-emo_Disgust-de-0-seed1702-scale0.5", "bucket": "emo_Disgust", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "0546b8c6c21a2552f8810e4a5f0d013b68ed6e12c51ae30a0711fb634226b9ff", "task_id": "emo_Disgust-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09799551218748093, "target_z": -0.25390625569883596, "ce": 6.1894097328186035, "genuineness": 4.7332844734191895, "identity": 0.7220797538757324, "hypothesis": "Die Tür 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_Disgust/de/90ad6ad9bef20a2902fea210.mp3" }, { "key": "original-emo_Disgust-de-0-seed1702-scale0.75", "bucket": "emo_Disgust", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "af917b1db321f9b514241d68ffdcca621ad6f8c1e9475d253c3f144bdcfb65c7", "task_id": "emo_Disgust-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08075946569442749, "target_z": -0.28906249620077606, "ce": 6.221180438995361, "genuineness": 4.319066047668457, "identity": 0.39997637271881104, "hypothesis": "Die Tür 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_Disgust/de/bcf58c332a9e35d93ca8b107.mp3" }, { "key": "original-emo_Disgust-de-0-seed1702-scale1.0", "bucket": "emo_Disgust", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "ffec559c310179e12f9b75b08a7909a711af8c38ff648b8fa2d252883dacd165", "task_id": "emo_Disgust-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05777806043624878, "target_z": -0.33593750379922394, "ce": 6.229123115539551, "genuineness": 4.607763767242432, "identity": 0.49557799100875854, "hypothesis": "Die Tür 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_Disgust/de/eb1e29a1a430c383846d52c7.mp3" }, { "key": "original-emo_Disgust-de-1-seed1701-scale0.0", "bucket": "emo_Disgust", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "a40613aa5c49847a4cd97ea3eeab766787d1fd0a05d40edc7009f700a61177bb", "task_id": "emo_Disgust-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02457195520401001, "target_z": -0.5039062405019401, "ce": 6.507116317749023, "genuineness": 4.607763767242432, "identity": 0.6399411559104919, "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_Disgust/de/f565020881cb488aa93b944e.mp3" }, { "key": "original-emo_Disgust-de-1-seed1701-scale0.5", "bucket": "emo_Disgust", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "461d03ff4fe4aa998f87bd1b911ac9daaf83966737a193e00823c1dfbf8e0cd8", "task_id": "emo_Disgust-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.018826603889465332, "target_z": -0.49218748860232814, "ce": 6.41180419921875, "genuineness": 4.381826400756836, "identity": 0.5845212340354919, "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/audio/emo_Disgust/de/f096f003f13c26ba538d20bd.mp3" }, { "key": "original-emo_Disgust-de-1-seed1701-scale0.75", "bucket": "emo_Disgust", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "58e171eda98cdc82b2acbce947e476c1151d2cd8d37e75dd0c923f0d6c4f5100", "task_id": "emo_Disgust-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0044632405042648315, "target_z": -0.46289063924708984, "ce": 6.3641486167907715, "genuineness": 4.557555198669434, "identity": 0.6622172594070435, "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_Disgust/de/92d555a38d1517dd3058881f.mp3" }, { "key": "original-emo_Disgust-de-1-seed1701-scale1.0", "bucket": "emo_Disgust", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "9179f0b2d59253354b6701396b26a65268ae39b743e68e28163276f13f345601", "task_id": "emo_Disgust-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0006330013275146484, "target_z": -0.455078127849418, "ce": 6.4515180587768555, "genuineness": 4.168440818786621, "identity": 0.3573596775531769, "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_Disgust/de/0d95ef0270b149c550ea3f57.mp3" }, { "key": "original-emo_Disgust-de-1-seed1702-scale0.0", "bucket": "emo_Disgust", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "77e57471991ba3cb279239a8d751b486c3b16b01ba3cd40d77d2e2fdafddc3bd", "task_id": "emo_Disgust-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.016911491751670837, "target_z": -0.48828124810038803, "ce": 6.4515180587768555, "genuineness": 4.545003414154053, "identity": 0.3739621341228485, "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_Disgust/de/212250a9723f91ea9f520743.mp3" }, { "key": "original-emo_Disgust-de-1-seed1702-scale0.5", "bucket": "emo_Disgust", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "9d3ce5e9234193497d4212e7cf7316dac0f526ae54ef6f708b50eaa332fd1b0e", "task_id": "emo_Disgust-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02457195520401001, "target_z": -0.5039062405019401, "ce": 6.348263263702393, "genuineness": 4.331617832183838, "identity": 0.5596143007278442, "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_Disgust/de/0ab2428a458fb6806c547952.mp3" }, { "key": "original-emo_Disgust-de-1-seed1702-scale0.75", "bucket": "emo_Disgust", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "56b135fb267e90883f207398eeccd1b93af1f761d4188855656848aba9b2d293", "task_id": "emo_Disgust-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.016911491751670837, "target_z": -0.48828124810038803, "ce": 6.38003396987915, "genuineness": 4.432034492492676, "identity": 0.6772529482841492, "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_Disgust/de/a757e9507f1a9abb8ecbf809.mp3" }, { "key": "original-emo_Disgust-de-1-seed1702-scale1.0", "bucket": "emo_Disgust", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "133fc64ea639d839fa73979d41074542a624ada7576f5b649bccccf9242c5579", "task_id": "emo_Disgust-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03223241865634918, "target_z": -0.5195312329034921, "ce": 6.435632705688477, "genuineness": 4.425758361816406, "identity": 0.5122143030166626, "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/audio/emo_Disgust/de/07ce86f32002712a6f283ff2.mp3" }, { "key": "original-emo_Disgust-en-0-seed1701-scale0.0", "bucket": "emo_Disgust", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "abcd43ab8ef3dc6040c03de046fce805349be6b221e9196319cc0a0de30e04a6", "task_id": "emo_Disgust-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06065073609352112, "target_z": -0.330078127849418, "ce": 6.173524379730225, "genuineness": 4.049196243286133, "identity": 0.3957890272140503, "hypothesis": "The 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_Disgust/en/1237e74289751e550eb59f81.mp3" }, { "key": "original-emo_Disgust-en-0-seed1701-scale0.5", "bucket": "emo_Disgust", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "10b0717c010f380a0cb1635c7d9b92001901423e023dd1dda90c0a2e485cda3e", "task_id": "emo_Disgust-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04820248484611511, "target_z": -0.3554687367027161, "ce": 6.157639026641846, "genuineness": 3.9173994064331055, "identity": 0.38505807518959045, "hypothesis": "The 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_Disgust/en/6bde85a80184f6a2a1b806b8.mp3" }, { "key": "original-emo_Disgust-en-0-seed1701-scale0.75", "bucket": "emo_Disgust", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "ea9309d69d73cf1bf3ea98cb42e4c9ffef10a5cf5bdb62dc936f951c375772f7", "task_id": "emo_Disgust-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04916003346443176, "target_z": -0.3535156316486419, "ce": 6.205295085906982, "genuineness": 3.923675537109375, "identity": 0.3829769790172577, "hypothesis": "The 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_Disgust/en/ce3ac416290bbed4106e86cc.mp3" }, { "key": "original-emo_Disgust-en-0-seed1701-scale1.0", "bucket": "emo_Disgust", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "1d9e6c93c7fc7e2fc042169e99f5338addfa977143a5a3ddef8195493789ac4c", "task_id": "emo_Disgust-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0663960874080658, "target_z": -0.318359375949806, "ce": 6.229123115539551, "genuineness": 4.482243061065674, "identity": 0.4215276539325714, "hypothesis": "The 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_Disgust/en/ecb974a2c95dc9796fcc3d27.mp3" }, { "key": "original-emo_Disgust-en-0-seed1702-scale0.0", "bucket": "emo_Disgust", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "eee8df6e55d9dc1affb588bfba086dcb0bb87dcfabc574052aed4e4df2e7de91", "task_id": "emo_Disgust-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02905130386352539, "target_z": -0.3945312632972839, "ce": 6.197352409362793, "genuineness": 3.8546390533447266, "identity": 0.25966501235961914, "hypothesis": "The 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_Disgust/en/757672ecb2fe8bc0622a5418.mp3" }, { "key": "original-emo_Disgust-en-0-seed1702-scale0.5", "bucket": "emo_Disgust", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.5, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "0d7f9372a29ae3f672310b74a7a97f996c334840047778f9648eacd44036b84b", "task_id": "emo_Disgust-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03479665517807007, "target_z": -0.38281251139767186, "ce": 6.165581703186035, "genuineness": 4.137060642242432, "identity": 0.3194282054901123, "hypothesis": "The 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_Disgust/en/01adf57db062908df8aad2d4.mp3" }, { "key": "original-emo_Disgust-en-0-seed1702-scale0.75", "bucket": "emo_Disgust", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "c7313592fd4fef34261f6d5525b60acd113a8cc95e4af4dad5af242473d7594f", "task_id": "emo_Disgust-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.039584457874298096, "target_z": -0.3730468645521341, "ce": 6.117925643920898, "genuineness": 3.5439748764038086, "identity": 0.6176971197128296, "hypothesis": "The 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_Disgust/en/a990f151cdc146cb1cdb5245.mp3" }, { "key": "original-emo_Disgust-en-0-seed1702-scale1.0", "bucket": "emo_Disgust", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "ecd99261b6e5e03218308fb0d3b3f88e3bf097069a4edbb8bfb5a5ae2b28799c", "task_id": "emo_Disgust-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02905130386352539, "target_z": -0.3945312632972839, "ce": 6.173524379730225, "genuineness": 3.550251007080078, "identity": 0.2933524549007416, "hypothesis": "The 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_Disgust/en/6440b2158b2274eaad57b26a.mp3" }, { "key": "original-emo_Disgust-en-1-seed1701-scale0.0", "bucket": "emo_Disgust", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "adf6fb93fb1259fe8b76c5ff7a8e248c9451664da2e9d0fb99cfae9966b583b9", "task_id": "emo_Disgust-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.07244987785816193, "target_z": -0.6015624962007761, "ce": 6.332377910614014, "genuineness": 4.808597087860107, "identity": 0.30156442523002625, "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_Disgust/en/0e6576087b7b8d99ecf1d8ac.mp3" }, { "key": "original-emo_Disgust-en-1-seed1701-scale0.5", "bucket": "emo_Disgust", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "0fc3b97912ec66b24adea3e69f40de055d4872458cd42efa3901bdfa101635be", "task_id": "emo_Disgust-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.06478939950466156, "target_z": -0.5859374734054322, "ce": 6.403861999511719, "genuineness": 4.632867813110352, "identity": 0.3652645945549011, "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_Disgust/en/c818cb6a2a36c66800c3275c.mp3" }, { "key": "original-emo_Disgust-en-1-seed1701-scale0.75", "bucket": "emo_Disgust", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "bec314a9a83ab0cac9a4e09263f8873f684b8f42c5fe4cf4e7c450f9dbb204de", "task_id": "emo_Disgust-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.045638248324394226, "target_z": -0.5468750075984479, "ce": 6.324435234069824, "genuineness": 4.507347106933594, "identity": 0.5392726063728333, "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_Disgust/en/2e5a85904ede09ededb02616.mp3" }, { "key": "original-emo_Disgust-en-1-seed1701-scale1.0", "bucket": "emo_Disgust", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "80096d1676dd35ead8ba1ff425d1af642c969d701927f708d65b39523ab38ab5", "task_id": "emo_Disgust-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05712895095348358, "target_z": -0.5703125113976719, "ce": 6.1894097328186035, "genuineness": 4.494794845581055, "identity": 0.41658663749694824, "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_Disgust/en/d27b1d3992d1eb3ca2d3d1b4.mp3" }, { "key": "original-emo_Disgust-en-1-seed1702-scale0.0", "bucket": "emo_Disgust", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "a03916e4f729e48ed518d730d13774d24a2b9fc2db64495de5c40757af5c35ec", "task_id": "emo_Disgust-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.06095917522907257, "target_z": -0.5781249924015521, "ce": 6.348263263702393, "genuineness": 4.469690799713135, "identity": 0.2614765763282776, "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_Disgust/en/0bf631cdeb943de0d48ea2c4.mp3" }, { "key": "original-emo_Disgust-en-1-seed1702-scale0.5", "bucket": "emo_Disgust", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "723280f03bb2aa4f6fce52285f1773cf17ecc660267b8836e8a8d0806089ba5f", "task_id": "emo_Disgust-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05904404819011688, "target_z": -0.5742187215058203, "ce": 6.332377910614014, "genuineness": 4.532451152801514, "identity": 0.457658976316452, "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_Disgust/en/9b5a5882f795f80b598bb83a.mp3" }, { "key": "original-emo_Disgust-en-1-seed1702-scale0.75", "bucket": "emo_Disgust", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "20192c8b909644761c72419c19e7d178082a9fbe35d08a5a68c7a1f28952b4d2", "task_id": "emo_Disgust-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03797776997089386, "target_z": -0.5312499848031041, "ce": 6.252951145172119, "genuineness": 4.375550270080566, "identity": 0.507979154586792, "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_Disgust/en/e7874141ed0e49e9fca3e07a.mp3" }, { "key": "original-emo_Disgust-en-1-seed1702-scale1.0", "bucket": "emo_Disgust", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "8e1fbc6a2895ed43d2aa1f72b6cd36387e087641797d3f4846c26f2d0d7417b2", "task_id": "emo_Disgust-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.053298696875572205, "target_z": -0.5624999696062083, "ce": 6.332377910614014, "genuineness": 4.457139015197754, "identity": 0.2860647141933441, "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_Disgust/en/7c2102fda4e45e107eec0e2d.mp3" }, { "key": "original-emo_Disgust-es-0-seed1701-scale0.0", "bucket": "emo_Disgust", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "9c9173d07ffe0bc220f553d5007f3f01aa3fbd4d6f6edae697d1c3405d2336d5", "task_id": "emo_Disgust-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12911616265773773, "target_z": -0.190429687974903, "ce": 6.054384231567383, "genuineness": 4.306513786315918, "identity": 0.5016223788261414, "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_Disgust/es/5534ba82e465bfa94ae59bb0.mp3" }, { "key": "original-emo_Disgust-es-0-seed1701-scale0.5", "bucket": "emo_Disgust", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.5, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "090653e1ae5aae86282af2f78decff07d22d14f948a06b31ff6bc25e39a884b5", "task_id": "emo_Disgust-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04149957001209259, "target_z": -0.369140624050194, "ce": 6.125868320465088, "genuineness": 4.074300289154053, "identity": 0.6531800627708435, "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_Disgust/es/f47b4616642d89080ce8a503.mp3" }, { "key": "original-emo_Disgust-es-0-seed1701-scale0.75", "bucket": "emo_Disgust", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "7fcf45314dacc4de9f5b9c0303fa77710c4ab08b7b00cc1ad514c506dc80352a", "task_id": "emo_Disgust-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.040542006492614746, "target_z": -0.3710937594980599, "ce": 6.229123115539551, "genuineness": 4.306513786315918, "identity": 0.6106752157211304, "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_Disgust/es/ee62c9202ef89e2005c5f440.mp3" }, { "key": "original-emo_Disgust-es-0-seed1701-scale1.0", "bucket": "emo_Disgust", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "746d76e06be4ae6ed98df63716c8916593091988b6f66acff2f1ceaeda3439f4", "task_id": "emo_Disgust-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.053947821259498596, "target_z": -0.34375001519689585, "ce": 6.165581703186035, "genuineness": 4.632867813110352, "identity": 0.634506344795227, "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_Disgust/es/19914021728633ac850e6fe8.mp3" }, { "key": "original-emo_Disgust-es-0-seed1702-scale0.0", "bucket": "emo_Disgust", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "f242c708e058c58499e119413621d8e4023701e1757c191e3416788c92ea337e", "task_id": "emo_Disgust-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032881543040275574, "target_z": -0.38671875189961197, "ce": 6.054384231567383, "genuineness": 4.607763767242432, "identity": 0.5859191417694092, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disgust/es/e37e3be2009ae44c501aedc9.mp3" }, { "key": "original-emo_Disgust-es-0-seed1702-scale0.5", "bucket": "emo_Disgust", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "3e21135ea7bef1e9c433d451e186cd10e1e6371551bbc1a31546403d46907f2b", "task_id": "emo_Disgust-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.040542006492614746, "target_z": -0.3710937594980599, "ce": 5.863759994506836, "genuineness": 3.735394239425659, "identity": 0.5305300354957581, "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_Disgust/es/240dfbd663eb15f3cdf028b7.mp3" }, { "key": "original-emo_Disgust-es-0-seed1702-scale0.75", "bucket": "emo_Disgust", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "2e18f47bdd308ed5c5ed4d319b02751fb1ebf1b7cb309d0dd1bc5c51bc41bd50", "task_id": "emo_Disgust-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07501411437988281, "target_z": -0.30078124810038803, "ce": 6.006728172302246, "genuineness": 4.231201171875, "identity": 0.6833505630493164, "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_Disgust/es/352304ca34997b5c6a940058.mp3" }, { "key": "original-emo_Disgust-es-0-seed1702-scale1.0", "bucket": "emo_Disgust", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "f69fe8c9fc8625ff1eba5343063c66b201bd0654a7844733129b3b43406ad79d", "task_id": "emo_Disgust-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04149957001209259, "target_z": -0.369140624050194, "ce": 6.0146708488464355, "genuineness": 3.973883628845215, "identity": 0.6892666816711426, "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_Disgust/es/3da45a6f8e12e1da244c3874.mp3" }, { "key": "original-emo_Disgust-es-1-seed1701-scale0.0", "bucket": "emo_Disgust", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "1264f35e6c80af7229aa6d93b4ad2935de4adc382491936aa677e011385ce00a", "task_id": "emo_Disgust-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0015905648469924927, "target_z": -0.4570312632972839, "ce": 6.117925643920898, "genuineness": 4.532451152801514, "identity": 0.8303206562995911, "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_Disgust/es/f9e5680d6fdb3ed0d2e77c21.mp3" }, { "key": "original-emo_Disgust-es-1-seed1701-scale0.5", "bucket": "emo_Disgust", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "e4b1b471db98dc2358f42e854125d824a15f9a666af43923bc5acf0c43a2fdd4", "task_id": "emo_Disgust-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03414754569530487, "target_z": -0.5234375037992239, "ce": 6.0146708488464355, "genuineness": 4.545003414154053, "identity": 0.5426994562149048, "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_Disgust/es/df9bb67aa93d91460ec2b158.mp3" }, { "key": "original-emo_Disgust-es-1-seed1701-scale0.75", "bucket": "emo_Disgust", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "6be48139b3f21ad8adbbc8be2f408856b3b8532efc764537ee5091c74c6c2844", "task_id": "emo_Disgust-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00733591616153717, "target_z": -0.46875001519689585, "ce": 6.1894097328186035, "genuineness": 4.6705241203308105, "identity": 0.7138437628746033, "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_Disgust/es/92d7afc08ce4b05d69e37c05.mp3" }, { "key": "original-emo_Disgust-es-1-seed1701-scale1.0", "bucket": "emo_Disgust", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "723bca875d9ef984c9b2d365f23353ce7c0625deefa0c86bb8290aa122460253", "task_id": "emo_Disgust-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.045638248324394226, "target_z": -0.5468750075984479, "ce": 6.213237762451172, "genuineness": 4.149612903594971, "identity": 0.7139976024627686, "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_Disgust/es/78549c6da0fa5d3cc5f41368.mp3" }, { "key": "original-emo_Disgust-es-1-seed1702-scale0.0", "bucket": "emo_Disgust", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "8658dd3c0a484b55fb012ed3a54266ad1ea5b8a21baa9350e0d18b922077dbbf", "task_id": "emo_Disgust-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.04180802404880524, "target_z": -0.5390625265945678, "ce": 6.109982967376709, "genuineness": 4.3127899169921875, "identity": 0.5507510900497437, "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_Disgust/es/c5476c1aa0e2f99dc876bfdd.mp3" }, { "key": "original-emo_Disgust-es-1-seed1702-scale0.5", "bucket": "emo_Disgust", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "0e184013339a7d306b13099d8a4097bf02fd75a35eb4aaa9748b486d4c295151", "task_id": "emo_Disgust-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.002548113465309143, "target_z": -0.4589843683513581, "ce": 6.054384231567383, "genuineness": 4.532451152801514, "identity": 0.5804761648178101, "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_Disgust/es/ad528b0b412ef825cfad785e.mp3" }, { "key": "original-emo_Disgust-es-1-seed1702-scale0.75", "bucket": "emo_Disgust", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "d6d56184d2807e48735fd822046ec2c112101243d188cf1df84c1830c2cb34bf", "task_id": "emo_Disgust-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01564548909664154, "target_z": -0.4218750075984479, "ce": 6.054384231567383, "genuineness": 4.720732688903809, "identity": 0.6539536118507385, "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_Disgust/es/c01a1403f469fb55e317e70f.mp3" }, { "key": "original-emo_Disgust-es-1-seed1702-scale1.0", "bucket": "emo_Disgust", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "8da5dee76706719087731f5ec62b5d580dedf10f54231b4d56890877446abfb2", "task_id": "emo_Disgust-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00733591616153717, "target_z": -0.46875001519689585, "ce": 6.062326908111572, "genuineness": 4.231201171875, "identity": 0.5564820766448975, "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_Disgust/es/e3bf9a9e690fff5d1573ebff.mp3" }, { "key": "original-emo_Disgust-fr-0-seed1701-scale0.0", "bucket": "emo_Disgust", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "c72398f4ef10bf6eeb122330441b52d50edba0b7df138c80eec2660718c0ac29", "task_id": "emo_Disgust-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0060699135065078735, "target_z": -0.4414062405019401, "ce": 5.990842819213867, "genuineness": 4.369274139404297, "identity": 0.7111908197402954, "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_Disgust/fr/af5562fd5440941dcd9168ee.mp3" }, { "key": "original-emo_Disgust-fr-0-seed1701-scale0.5", "bucket": "emo_Disgust", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "81b72ca425efee13bac23eb3977ec1a5d2a46ccb9d455ad1a97fe374d1356eb5", "task_id": "emo_Disgust-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012772813439369202, "target_z": -0.42773438354825394, "ce": 6.006728172302246, "genuineness": 4.369274139404297, "identity": 0.7558548450469971, "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_Disgust/fr/e3eb8654d02513823fc6d1b3.mp3" }, { "key": "original-emo_Disgust-fr-0-seed1701-scale0.75", "bucket": "emo_Disgust", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "416944415047087827f1b25ac27370406e224ac32d03b06f18f7ca3e3f16916a", "task_id": "emo_Disgust-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022348403930664062, "target_z": -0.40820312025097005, "ce": 6.054384231567383, "genuineness": 4.406930446624756, "identity": 0.7359665632247925, "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_Disgust/fr/4c85235106df43ba00f71097.mp3" }, { "key": "original-emo_Disgust-fr-0-seed1701-scale1.0", "bucket": "emo_Disgust", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "3ca2dea36e2291cadd08284996a7636d6bc3aa46e9d0e701613b0fcb67661bdb", "task_id": "emo_Disgust-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004154786467552185, "target_z": -0.44531251139767186, "ce": 6.24500846862793, "genuineness": 4.632867813110352, "identity": 0.7526292204856873, "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_Disgust/fr/7724a9916fe85ec7886966ae.mp3" }, { "key": "original-emo_Disgust-fr-0-seed1702-scale0.0", "bucket": "emo_Disgust", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "b85f61f17a965499e277dbd005de44c9711d9fed0c716c13772b0042f6c8b3cf", "task_id": "emo_Disgust-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0060699135065078735, "target_z": -0.4414062405019401, "ce": 6.09409761428833, "genuineness": 4.444586753845215, "identity": 0.6260559558868408, "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_Disgust/fr/6c4b08c32a91d9820e6b0333.mp3" }, { "key": "original-emo_Disgust-fr-0-seed1702-scale0.5", "bucket": "emo_Disgust", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "9ab4494304ecd3933913c0afed1b636ba20be9a8e130a413a0c5792998dfb1ca", "task_id": "emo_Disgust-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01116614043712616, "target_z": -0.47656249620077606, "ce": 6.09409761428833, "genuineness": 4.582659721374512, "identity": 0.7450015544891357, "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_Disgust/fr/bc629c45be9c24113c7232dd.mp3" }, { "key": "original-emo_Disgust-fr-0-seed1702-scale0.75", "bucket": "emo_Disgust", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "20072ef8f2ccdd66cf6a1473031159694524d987f680f6f5affc0edc538bc986", "task_id": "emo_Disgust-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04820248484611511, "target_z": -0.3554687367027161, "ce": 6.157639026641846, "genuineness": 4.6203155517578125, "identity": 0.6264728903770447, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disgust/fr/a662c550eb7fa2d13f227fbd.mp3" }, { "key": "original-emo_Disgust-fr-0-seed1702-scale1.0", "bucket": "emo_Disgust", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "48e6d030a568deb7c2180e6793586fb16c936f952748486021eefdb881b92c35", "task_id": "emo_Disgust-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07118387520313263, "target_z": -0.3085937594980599, "ce": 6.173524379730225, "genuineness": 4.381826400756836, "identity": 0.7832876443862915, "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_Disgust/fr/01276732c1c3f44f460d221f.mp3" }, { "key": "original-emo_Disgust-fr-1-seed1701-scale0.0", "bucket": "emo_Disgust", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "78f1310df0282cffb996074141a214370a0e13f21a2723f17b01aef40fe6853a", "task_id": "emo_Disgust-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.07053475081920624, "target_z": -0.5976562253050443, "ce": 6.173524379730225, "genuineness": 4.369274139404297, "identity": 0.8101232647895813, "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_Disgust/fr/992384c443187b1c60556e47.mp3" }, { "key": "original-emo_Disgust-fr-1-seed1701-scale0.5", "bucket": "emo_Disgust", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "579192030f96c53e67d9813beea6a01707fc39c1e2c84cdfcf5c93adbfe968d2", "task_id": "emo_Disgust-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.049468472599983215, "target_z": -0.5546874886023281, "ce": 6.1894097328186035, "genuineness": 4.582659721374512, "identity": 0.7681502103805542, "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_Disgust/fr/88dd4ddfeb4839bb94dc32e9.mp3" }, { "key": "original-emo_Disgust-fr-1-seed1701-scale0.75", "bucket": "emo_Disgust", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "12c205156f3d024553d5d4a4fbc8af68f08f85e5e9a4ec76897d45d693223991", "task_id": "emo_Disgust-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.026487082242965698, "target_z": -0.5078125113976719, "ce": 6.23706579208374, "genuineness": 4.582659721374512, "identity": 0.7976937294006348, "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_Disgust/fr/423125c7dddf09abe69ba070.mp3" }, { "key": "original-emo_Disgust-fr-1-seed1701-scale1.0", "bucket": "emo_Disgust", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "d50f85d0440996b6e62fa495074e1046e6214584d29ee643598de36aa3a19819", "task_id": "emo_Disgust-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05712895095348358, "target_z": -0.5703125113976719, "ce": 6.197352409362793, "genuineness": 4.519899368286133, "identity": 0.6029440760612488, "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_Disgust/fr/5f89bc72f8bbee54e6603570.mp3" }, { "key": "original-emo_Disgust-fr-1-seed1702-scale0.0", "bucket": "emo_Disgust", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "511397d1cb0e36c806448080ce568907e462b11a64e72465d8c4ef11b2edb135", "task_id": "emo_Disgust-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0015905648469924927, "target_z": -0.4570312632972839, "ce": 6.1894097328186035, "genuineness": 4.65797233581543, "identity": 0.8413980007171631, "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_Disgust/fr/326f84cd43718476a2fe1f07.mp3" }, { "key": "original-emo_Disgust-fr-1-seed1702-scale0.5", "bucket": "emo_Disgust", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "8eb6a6e638f1d595f9309f5a3bf5dade4a72606b77bd962170aa630edbe8e210", "task_id": "emo_Disgust-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.053298696875572205, "target_z": -0.5624999696062083, "ce": 6.117925643920898, "genuineness": 4.582659721374512, "identity": 0.745764970779419, "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_Disgust/fr/f9147f27662d2e1fa415d6ba.mp3" }, { "key": "original-emo_Disgust-fr-1-seed1702-scale0.75", "bucket": "emo_Disgust", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "6a39f35fedc653b5cea1894a4166b9037f13a1197aff70663683c503a923dfdd", "task_id": "emo_Disgust-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.045638248324394226, "target_z": -0.5468750075984479, "ce": 6.23706579208374, "genuineness": 4.607763767242432, "identity": 0.7735224962234497, "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_Disgust/fr/95434b1d571b7bd1a321d098.mp3" }, { "key": "original-emo_Disgust-fr-1-seed1702-scale1.0", "bucket": "emo_Disgust", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "d63a36e5c480ab369646e2b9e6134af664ed9597b3890ff27c39f74403ce497b", "task_id": "emo_Disgust-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.016911491751670837, "target_z": -0.48828124810038803, "ce": 6.0146708488464355, "genuineness": 4.344170093536377, "identity": 0.6361388564109802, "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_Disgust/fr/93b661fbd0f54d12f8946929.mp3" }, { "key": "original-emo_Disgust-nl-0-seed1701-scale0.0", "bucket": "emo_Disgust", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "3c90e400e01f903e5ff27abeb2de3deef32aebe000498b1563e10fd1aa4ad5db", "task_id": "emo_Disgust-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": 0.08554725348949432, "target_z": -0.27929687974902995, "ce": 6.197352409362793, "genuineness": 4.243753433227539, "identity": 0.5892766118049622, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disgust/nl/d9581faec7426be6301fe348.mp3" }, { "key": "original-emo_Disgust-nl-0-seed1701-scale0.5", "bucket": "emo_Disgust", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "431b720b888ce6dd45d728445aa7f6c230a4d47655fce08854a51323044b7df3", "task_id": "emo_Disgust-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": 0.0663960874080658, "target_z": -0.318359375949806, "ce": 6.229123115539551, "genuineness": 4.381826400756836, "identity": 0.5848616361618042, "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_Disgust/nl/fa17700e8563844589b41558.mp3" }, { "key": "original-emo_Disgust-nl-0-seed1701-scale0.75", "bucket": "emo_Disgust", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "24528583505cf6dd8ff141471f550c41d2dc8640defde880049ab710992d0e4d", "task_id": "emo_Disgust-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": 0.07309900224208832, "target_z": -0.30468748860232814, "ce": 6.23706579208374, "genuineness": 4.356721878051758, "identity": 0.4629228115081787, "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_Disgust/nl/20fab9593124d39e83d10702.mp3" }, { "key": "original-emo_Disgust-nl-0-seed1701-scale1.0", "bucket": "emo_Disgust", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "a00d8b243ae2d3bfcb97563a4be28393ac8e2dbc58f294e6b2f47372864e9499", "task_id": "emo_Disgust-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": 0.0893774926662445, "target_z": -0.2714843683513581, "ce": 6.173524379730225, "genuineness": 4.306513786315918, "identity": 0.7057598829269409, "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_Disgust/nl/e1505712d98a4f442dd50119.mp3" }, { "key": "original-emo_Disgust-nl-0-seed1702-scale0.0", "bucket": "emo_Disgust", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "d2283d1c9e4d591d974b51e67deee3a932a31af232b3b26b4993a0bdcc33012f", "task_id": "emo_Disgust-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": 0.03766933083534241, "target_z": -0.3769531354478659, "ce": 6.006728172302246, "genuineness": 4.344170093536377, "identity": 0.4646134376525879, "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_Disgust/nl/25131158d738aa1c0ef280f4.mp3" }, { "key": "original-emo_Disgust-nl-0-seed1702-scale0.5", "bucket": "emo_Disgust", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "c758b064a77f24a6567b65702b89b788346964e68e81e6b10a6842faa4fb5542", "task_id": "emo_Disgust-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": 0.07597167789936066, "target_z": -0.2988281126525221, "ce": 6.117925643920898, "genuineness": 4.18099308013916, "identity": 0.7286052703857422, "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_Disgust/nl/d82c316f8b92aaed565bd0bb.mp3" }, { "key": "original-emo_Disgust-nl-0-seed1702-scale0.75", "bucket": "emo_Disgust", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "62c325fac9082e00718274cb6c963a4efff2964ba3dcc96db53b99ae3440e9bf", "task_id": "emo_Disgust-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": 0.06352341175079346, "target_z": -0.32421875189961197, "ce": 5.998785495758057, "genuineness": 4.394378662109375, "identity": 0.6196815967559814, "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_Disgust/nl/e1136f0cf85c63d4118627e8.mp3" }, { "key": "original-emo_Disgust-nl-0-seed1702-scale1.0", "bucket": "emo_Disgust", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "6d4dc0bfdd0a3afcc6f0367fec23beb245759104a37390f2eb42f31a4fef5f22", "task_id": "emo_Disgust-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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": 0.08171702921390533, "target_z": -0.28710936075291016, "ce": 6.1894097328186035, "genuineness": 4.457139015197754, "identity": 0.5811353921890259, "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_Disgust/nl/04d1868b303a7ee8bb048f7d.mp3" }, { "key": "original-emo_Disgust-nl-1-seed1701-scale0.0", "bucket": "emo_Disgust", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "10c0597e243a5fecc3eff0ee227662636f8517233b08eb98331e9f036f5932d4", "task_id": "emo_Disgust-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03862689435482025, "target_z": -0.375, "ce": 6.149696350097656, "genuineness": 4.482243061065674, "identity": 0.5584689974784851, "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_Disgust/nl/11f840381fb24789a91eefcf.mp3" }, { "key": "original-emo_Disgust-nl-1-seed1701-scale0.5", "bucket": "emo_Disgust", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "2b6a35d77eedbfec7c68c123146b05e88fe8aa3e31f14d05371c2b8dfd66b9c6", "task_id": "emo_Disgust-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04437224566936493, "target_z": -0.36328124810038803, "ce": 6.1894097328186035, "genuineness": 4.394378662109375, "identity": 0.451849102973938, "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_Disgust/nl/7734054b6ebdfcd0aa5a3c7d.mp3" }, { "key": "original-emo_Disgust-nl-1-seed1701-scale0.75", "bucket": "emo_Disgust", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "126593b588b0f90aaf8cdbf3b4414a7480d9c3104fe1c16ce1dfe5db874e6958", "task_id": "emo_Disgust-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.043414682149887085, "target_z": -0.36523438354825394, "ce": 6.229123115539551, "genuineness": 4.375550270080566, "identity": 0.6535528898239136, "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_Disgust/nl/abf17e99ce7ff840f8e27cb8.mp3" }, { "key": "original-emo_Disgust-nl-1-seed1701-scale1.0", "bucket": "emo_Disgust", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "05e0e1330b90dd63cef7e135f9f5177c59575e11c3789d8df2d3345d3a917bc5", "task_id": "emo_Disgust-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03671178221702576, "target_z": -0.3789062405019401, "ce": 6.157639026641846, "genuineness": 4.369274139404297, "identity": 0.7255312204360962, "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_Disgust/nl/c101468a911797d238c49d83.mp3" }, { "key": "original-emo_Disgust-nl-1-seed1702-scale0.0", "bucket": "emo_Disgust", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "6d9d1114883a5ac66c9005a90fe74d6f8ad2f954a8f31de87e3116f2a433eb16", "task_id": "emo_Disgust-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04820248484611511, "target_z": -0.3554687367027161, "ce": 6.284721851348877, "genuineness": 4.494794845581055, "identity": 0.6944600939750671, "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_Disgust/nl/39a34a2049b45c4856e7a2cd.mp3" }, { "key": "original-emo_Disgust-nl-1-seed1702-scale0.5", "bucket": "emo_Disgust", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "a0ae378c032d89d4a6b187516fe00ccf57536b14ba2e3c748dc32abb55ae59c2", "task_id": "emo_Disgust-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.042457133531570435, "target_z": -0.36718748860232814, "ce": 6.252951145172119, "genuineness": 4.369274139404297, "identity": 0.6086688041687012, "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_Disgust/nl/4b17441c3fe68806d8e62e53.mp3" }, { "key": "original-emo_Disgust-nl-1-seed1702-scale0.75", "bucket": "emo_Disgust", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "2ac2a7457a9226ec40dc5c0279c4f29daf5eb89143c3af2df020b8b9b84f6bf2", "task_id": "emo_Disgust-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05011759698390961, "target_z": -0.35156249620077606, "ce": 6.268836498260498, "genuineness": 4.256305694580078, "identity": 0.738918662071228, "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_Disgust/nl/26dae0b8509d0e5a9783e72d.mp3" }, { "key": "original-emo_Disgust-nl-1-seed1702-scale1.0", "bucket": "emo_Disgust", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "78aea2698959d6ea9be9cad3cd67c83f760fd1168cbd480c93f666c48d2113e8", "mp3_sha256": "dbbf0f2a381f5e71786231b1c48827b406785efbf3d3f808258df2e105428a6f", "task_id": "emo_Disgust-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disgust. 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 Disgust. 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 Disgust. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03671178221702576, "target_z": -0.3789062405019401, "ce": 6.173524379730225, "genuineness": 4.419482707977295, "identity": 0.44846463203430176, "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_Disgust/nl/d79dd04cb5f2434bbc289070.mp3" } ], "source_standard_audio_unchanged": true }