{ "complete": true, "report": { "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "label": "Intense Intoxication Altered States of Consciousness", "definition": { "id": "emo_Intoxication_Altered_States_of_Consciousness", "category": "emotion", "head": "emo_Intoxication_Altered_States_of_Consciousness", "pole": "high", "label": "Intense Intoxication Altered States of Consciousness", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_intoxication_altered_states_of_consciousness/full-v2-sealed/sealed-selected", "mission": "emotion_intoxication_altered_states_of_consciousness", "format_status": "CANONICAL", "heldout": true, "qualified": true, "source_cfg": 2.5, "source_model": { "label": "Humaneness 1.5 + real-speech rank 4", "repo": "laion/Humaneness-Voice-Large-1.5-RealSpeech-LoRAs", "revision": "fed33e554f094fcdc89fc0124aed2f9d42018714", "rank": 4 }, "metrics": { "ce": 6.3403204870223995, "genuineness": 4.549082775115966, "wer": 0.009589368510739478, "identity": 0.6199124550819397, "voiceclap": -0.09240224739536643, "fitness": 0.5445822280213664, "steering_v2": 0.40354691169201573, "raw_target": 0.0365608536452055, "target_cdf": 0.40354691169201573, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.33857307434082, "genuineness": 4.551781492233276, "wer": 0.007681669572798605, "identity": 0.6199124550819397, "fitness": 0.545148415595451, "steering_v2": 0.40245019046694974 }, "none": { "n": 50, "ce": 6.34206789970398, "genuineness": 4.546384057998657, "wer": 0.011497067448680351, "identity": null, "fitness": 0.5440160404472818, "steering_v2": 0.4046436329170818 } } } } ], "selected_wording": { "id": "manual-85e4ed8b7889", "general": "Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.", "inline": [ "Initiate with a breathy quality that seems too voluminous for the intended words.", "Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.", "Let the final articulation feel slightly weighted down, as if the effort to speak is considerable." ], "cfg": 2.5, "recipe": "P06", "strategy": "local-Gemma-mutation", "timing_syntax": "canonical", "canonical_labels": true, "neutral_event": "keep", "parent": "cfg-2.5", "origin": "exact_frozen_manual_recipe" }, "selection": { "manual_no_adapter": { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": -0.21340331970030046, "target_raw": 0.05376605242490769, "ce": 5.9944170951843265, "genuineness": 4.58893563747406, "identity": 0.5633997946977616, "wer": 0.008187134502923975, "valid_fraction": 1, "identity_delta": 0.02923153042793274, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": -0.16499023266921325, "target_raw": 0.08069415725767612, "ce": 5.874681353569031, "genuineness": 4.605880951881408, "identity": 0.555384760349989, "wer": 0.0813048245614035, "valid_fraction": 0.9, "identity_delta": 0.02121649608016014, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": -0.21340331970030046, "target_raw": 0.05376605242490769, "ce": 5.9944170951843265, "genuineness": 4.58893563747406, "identity": 0.5633997946977616, "wer": 0.008187134502923975, "valid_fraction": 1, "identity_delta": 0.02923153042793274, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": -0.2223144562121601, "target_raw": 0.048809541016817094, "ce": 6.120507025718689, "genuineness": 4.55159318447113, "identity": 0.5916851788759232, "wer": 0.005555555555555555, "valid_fraction": 1, "identity_delta": 0.05751691460609436, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": -0.22810058669620883, "target_raw": 0.045591206103563306, "ce": 5.935442805290222, "genuineness": 4.644164800643921, "identity": 0.5050340332090855, "wer": 0.010818713450292398, "valid_fraction": 1, "identity_delta": -0.02913423106074333, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": -0.22834472777120166, "target_raw": 0.045455411076545715, "ce": 6.052398610115051, "genuineness": 4.56289005279541, "identity": 0.6007820665836334, "wer": 0.013797514619883041, "valid_fraction": 1, "identity_delta": 0.06661380231380462, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": -0.24663085691573688, "target_raw": 0.03528438434004784, "ce": 6.195763874053955, "genuineness": 4.554731273651123, "identity": 0.5532726563513279, "wer": 0.008187134502923975, "valid_fraction": 1, "identity_delta": 0.0191043920814991, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": -0.26064453332206, "target_raw": 0.027489761635661126, "ce": 6.063915467262268, "genuineness": 4.607449913024903, "identity": 0.5907872200012207, "wer": 0.01608187134502924, "valid_fraction": 0.95, "identity_delta": 0.056618955731391904, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": -0.2675292959645494, "target_raw": 0.02366035059094429, "ce": 6.160021829605102, "genuineness": 4.455569815635681, "identity": 0.5830455109477043, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": 0.04887724667787552, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": -0.2695312518418311, "target_raw": 0.022546831890940665, "ce": 6.159624671936035, "genuineness": 4.4847533941268924, "identity": 0.5796348974108696, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.0454666331410408, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": -0.16499023266921325, "target_raw": 0.08069415725767612, "ce": 5.874681353569031, "genuineness": 4.605880951881408, "identity": 0.555384760349989, "wer": 0.0813048245614035, "valid_fraction": 0.9, "identity_delta": 0.02121649608016014, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": -0.16796875150695273, "target_raw": 0.07903745919466018, "ce": 6.002558445930481, "genuineness": 4.553789794445038, "identity": 0.5338301554322242, "wer": 0.02414000687994496, "valid_fraction": 0.95, "identity_delta": -0.0003381088376045227, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": -0.18997192486807934, "target_raw": 0.06679895520210266, "ce": 6.045845937728882, "genuineness": 4.605567145347595, "identity": 0.5533286519348621, "wer": 0.019499269005847954, "valid_fraction": 0.95, "identity_delta": 0.019160387665033342, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": -0.21967773434360516, "target_raw": 0.050276126340031625, "ce": 5.976148986816407, "genuineness": 4.628474736213684, "identity": 0.5740330711007118, "wer": 0.01985380116959064, "valid_fraction": 1, "identity_delta": 0.039864806830883025, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": -0.21977539090755363, "target_raw": 0.05022180825471878, "ce": 6.179878520965576, "genuineness": 4.495736455917358, "identity": 0.5214914068579674, "wer": 0.04429824561403509, "valid_fraction": 0.95, "identity_delta": -0.01267685741186142, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": -0.22153320102154517, "target_raw": 0.04924408718943596, "ce": 5.965625, "genuineness": 4.615608787536621, "identity": 0.5389180231839419, "wer": 0.026513157894736843, "valid_fraction": 1, "identity_delta": 0.0047497589141130446, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": -0.2225463876213519, "target_raw": 0.04868053719401359, "ce": 5.952519536018372, "genuineness": 4.651068449020386, "identity": 0.6008110992610455, "wer": 0.03305813553491572, "valid_fraction": 0.95, "identity_delta": 0.06664283499121666, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": -0.22325439486351215, "target_raw": 0.04828673265874386, "ce": 5.940804100036621, "genuineness": 4.654206371307373, "identity": 0.5730356216430664, "wer": 0.02805082559339525, "valid_fraction": 1, "identity_delta": 0.03886735737323761, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": -0.22396240344518592, "target_raw": 0.047892927378416064, "ce": 6.016259479522705, "genuineness": 4.647616553306579, "identity": 0.5811519637703896, "wer": 0.016282894736842104, "valid_fraction": 0.95, "identity_delta": 0.04698369950056076, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": -0.22416992489937038, "target_raw": 0.047777500748634336, "ce": 6.116734218597412, "genuineness": 4.615608835220337, "identity": 0.5941127657890319, "wer": 0.018680555555555554, "valid_fraction": 0.95, "identity_delta": 0.059944501519203185, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": -0.22963867037851224, "target_raw": 0.044735700264573096, "ce": 6.011295247077942, "genuineness": 4.580149126052857, "identity": 0.5720978230237961, "wer": 0.01686769005847953, "valid_fraction": 0.95, "identity_delta": 0.03792955875396729, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": -0.23018799081115152, "target_raw": 0.044430159777402875, "ce": 6.088934898376465, "genuineness": 4.572304153442383, "identity": 0.5762349873781204, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": 0.042066723108291626, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": -0.23706054847613728, "target_raw": 0.04060753732919693, "ce": 6.108394432067871, "genuineness": 4.533078861236572, "identity": 0.5633633524179459, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.029195088148117065, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": -0.2403198246608941, "target_raw": 0.03879467770457268, "ce": 6.088140654563904, "genuineness": 4.576383519172668, "identity": 0.580139872431755, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.04597160816192627, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": -0.2473632794709586, "target_raw": 0.03487699963152409, "ce": 6.120507025718689, "genuineness": 4.551279377937317, "identity": 0.5960213400423526, "wer": 0.019353070175438594, "valid_fraction": 1, "identity_delta": 0.06185307577252388, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": -0.24906616082349434, "target_raw": 0.03392983078956604, "ce": 6.109585857391357, "genuineness": 4.587366604804993, "identity": 0.5924403727054596, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.0582721084356308, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": -0.2535400415688554, "target_raw": 0.03144138939678669, "ce": 6.16161036491394, "genuineness": 4.458394002914429, "identity": 0.5519791692495346, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.017810904979705812, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": -0.25710449242296135, "target_raw": 0.02945878691971302, "ce": 6.150093460083008, "genuineness": 4.474397897720337, "identity": 0.5454873608425259, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.011319096572697163, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": -0.2597167962994278, "target_raw": 0.028005783259868623, "ce": 6.135399532318115, "genuineness": 4.519899201393128, "identity": 0.5628823362290859, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.028714071959257126, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": -0.2674316414098712, "target_raw": 0.023714667558670043, "ce": 6.129045414924621, "genuineness": 4.467180490493774, "identity": 0.585383453220129, "wer": 0.01067251461988304, "valid_fraction": 1, "identity_delta": 0.051215188950300215, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": -0.26796875083719596, "target_raw": 0.02341591902077198, "ce": 6.124478340148926, "genuineness": 4.4163445353508, "identity": 0.5118435844779015, "wer": 0.014707602339181286, "valid_fraction": 1, "identity_delta": -0.022324679791927336, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": -0.2726562518418311, "target_raw": 0.020808658748865127, "ce": 6.137385201454163, "genuineness": 4.504522895812988, "identity": 0.5861978344619274, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": 0.05202957019209862, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": -0.27543945353313304, "target_raw": 0.019260599091649056, "ce": 6.138973736763001, "genuineness": 4.510171341896057, "identity": 0.5511555194854736, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.016987255215644835, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": -0.27705078248486403, "target_raw": 0.018364353105425835, "ce": 6.160418939590454, "genuineness": 4.4963640689849855, "identity": 0.5898816987872124, "wer": 0.005555555555555555, "valid_fraction": 1, "identity_delta": 0.05571343451738357, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": -0.26083984511044345, "target_raw": 0.027381126210093497, "ce": 6.183849883079529, "genuineness": 4.329735147953033, "identity": 0.5341682642698288, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.5, "n": 20, "target_z": -0.2710937468186554, "target_raw": 0.02167774811387062, "ce": 6.210854935646057, "genuineness": 4.356094563007355, "identity": 0.533493971079588, "wer": 0.008388157894736842, "valid_fraction": 1, "identity_delta": -0.00067429319024086, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": -0.24916992355985687, "target_raw": 0.03387211635708809, "ce": 6.193381071090698, "genuineness": 4.430151796340942, "identity": 0.5761941522359848, "wer": 0.005756578947368421, "valid_fraction": 1, "identity_delta": 0.04202588796615601, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": -0.26186523333897, "target_raw": 0.026810789480805397, "ce": 6.1500934839248655, "genuineness": 4.3833952903747555, "identity": 0.5803677454590798, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.04619948118925095, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": -0.2781445315806924, "target_raw": 0.017755993008613587, "ce": 6.242625637054443, "genuineness": 4.375926818847656, "identity": 0.5795974230766296, "wer": 0.011393939393939394, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": -0.21186523427662948, "target_raw": 0.054621559232473374, "ce": 6.081230525970459, "genuineness": 4.613537731170655, "identity": 0.5934282898902893, "wer": 0.02131649281306032, "valid_fraction": 0.98, "identity_delta": 0.013830866813659668, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": -0.19067382754524181, "target_raw": 0.06640854611992836, "ce": 6.006331100463867, "genuineness": 4.593956460952759, "identity": 0.5864316427707672, "wer": 0.03685500312044934, "valid_fraction": 0.96, "identity_delta": 0.006834219694137573, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": -0.20488281239116451, "target_raw": 0.05850528985261917, "ce": 5.9865538597106935, "genuineness": 4.556425752639771, "identity": 0.5735473555326461, "wer": 0.026866741953698474, "valid_fraction": 1, "identity_delta": -0.006050067543983459, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": 0.014208984845922723, "ci95_z": [ -0.023652344909516402, 0.06751953573318434 ], "language_deltas": { "en": -0.028906251841831113, "de": 0.009374999330243241, "fr": 0.0035156202279830683, "nl": 0.11904297705916984, "es": -0.03198242054595143 }, "languages_improved": 3, "clear_gain": false, "delta_ce": 0.019777240753173827, "delta_genuineness": 0.037530708312988284, "delta_wer": 0.009988261166750868, "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": 0.021191406731387676, "ci95_z": [ -0.003496094407198824, 0.051074220729968436 ], "language_deltas": { "en": -0.0012695319825464595, "de": 0.008398439048812517, "fr": 0.032226561620944255, "nl": 0.07827148852958493, "es": -0.01166992355985686 }, "languages_improved": 3, "clear_gain": false, "delta_ce": -0.0748994255065918, "delta_genuineness": -0.01958127021789551, "delta_wer": 0.015538510307389026, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 0.06627929730406293, "ci95_z": [ 0.028730468017453537, 0.1263378924479942 ], "language_deltas": { "en": 0.035449218184892724, "de": 0.03154296902208869, "fr": 0.022558591929098794, "nl": 0.18364258146331888, "es": 0.05820312592091555 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.16139511108398438, "delta_genuineness": 0.23761091232299805, "delta_wer": 0.009922553419120924, "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": 1793035586.6646357, "example": { "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "sentences": [ "Je bericht kwam nadat ik vertrokken was.", "Ik las het twee keer... en legde mijn telefoon weg.", "Zeg maar wanneer we kunnen praten." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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.", "language": "nl", "seed": 1702, "scale": 0.0, "cfg": 4.0, "frames": 128, "reference": true } }, "rows": [ { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "000468545a9ef3f6a6b97bfc1a70a05a849af0c457cd42d8ae11b12f770576ca", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a67bdd10fee9eb0e0b8cc5cd28a40e081457a83bc59d0f538b43aecaa0c02711", "generation_seconds_batch": 26.977900256984867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.284721851348877, "genuineness": 4.607763767242432, "identity": 0.27854037284851074, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/000468545a9ef3f6a6b97bfc1a70a05a849af0c457cd42d8ae11b12f770576ca.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "00225edc4328ce12313f553fd680e11f4feeabcc77fe0a7caead9d3f9b72b8e3", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "wording", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1dd1ab0467d5ce03bb1a5f7510a4a00ed7a62e6c45ac594cca5e8bcc4898ccc4", "generation_seconds_batch": 16.696726626018062, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013855963945388794, "target_z": -0.2851562558603717, "ce": 6.078212261199951, "genuineness": 4.419482707977295, "identity": 0.8626906871795654, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/00225edc4328ce12313f553fd680e11f4feeabcc77fe0a7caead9d3f9b72b8e3.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": "00919f7b9f4c454e4b302102647ef6db3ccdcd74c9c671b3a987c48f2e2bc994", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "675166b9d7615fc5c848eca272d91fd31ddadb1dea4327f17d79996604eafb31", "generation_seconds_batch": 15.999899087008089, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05513758212327957, "target_z": -0.21093749497682426, "ce": 6.1894097328186035, "genuineness": 4.457139015197754, "identity": 0.6385946273803711, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.043478260869565216, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/00919f7b9f4c454e4b302102647ef6db3ccdcd74c9c671b3a987c48f2e2bc994.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": "00a6cf305979f00ea169c88345e2ada7c0dbdf30c789043c1524fadef09b60da", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "5c1aa5a161acbaeb73ef9aa4e226fe57e7b79e62d799a497e33b6e99ad18d760", "generation_seconds_batch": 15.93720739101991, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1099986732006073, "target_z": -0.1123046801745354, "ce": 6.0146708488464355, "genuineness": 4.457139015197754, "identity": 0.7021925449371338, "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_Intoxication_Altered_States_of_Consciousness/00a6cf305979f00ea169c88345e2ada7c0dbdf30c789043c1524fadef09b60da.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": "00c102859c221d6cd7b860cb42c6b1216d8e592c85f1e9d25d0424faf8f004cc", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "773cf0be82b7b23af1e342c800ac4a92758a0637037f43c42cd1a60e861aa5af", "generation_seconds_batch": 16.726510993903503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10239416360855103, "target_z": -0.1259765589419172, "ce": 6.022613525390625, "genuineness": 4.632867813110352, "identity": 0.5478876233100891, "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_Intoxication_Altered_States_of_Consciousness/00c102859c221d6cd7b860cb42c6b1216d8e592c85f1e9d25d0424faf8f004cc.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "018a942597a50c20ae83305fba6ba980a81c8bc542d4cb01fccd9362cb740836", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "85ba0e564c3c2ae9f0d88eb2be4879a0be9584819a0378dbf06227a4a266a880", "generation_seconds_batch": 18.00209329405334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02146047353744507, "target_z": -0.2714843770929899, "ce": 6.070269584655762, "genuineness": 4.607763767242432, "identity": 0.4284103512763977, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/018a942597a50c20ae83305fba6ba980a81c8bc542d4cb01fccd9362cb740836.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "01e5d5efe6974adf62323a661e6bc3d94f645039bb326e386352dbd24a18f23b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ddeb24a66c37f2c23e786aaacf045577c9beedead87cffacc9aaf4ea4dc653ff", "generation_seconds_batch": 16.141318134963512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04427400231361389, "target_z": -0.2304687407908445, "ce": 5.839932441711426, "genuineness": 4.645420074462891, "identity": 0.7816600799560547, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi dis-moi quand tu es prêt.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/01e5d5efe6974adf62323a661e6bc3d94f645039bb326e386352dbd24a18f23b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "01ea532f9a4f28a509ec1f2567825e0c771ae4c16198e588f6b2c7592df03426", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aeda029928cc79fe67eea21c47e7e7bb90f228227964033e90e8104273a3cb8e", "generation_seconds_batch": 24.23090731690172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01656205952167511, "target_z": -0.3398437441396283, "ce": 5.935244083404541, "genuineness": 4.6956281661987305, "identity": 0.7021017074584961, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/01ea532f9a4f28a509ec1f2567825e0c771ae4c16198e588f6b2c7592df03426.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "fb7f24c67f3fd85db43f2dc85accde20e82ac1a5566df4c39011c392f6f09901", "generation_seconds_batch": 17.799957466078922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01928776502609253, "target_z": -0.27539061286065863, "ce": 6.0305562019348145, "genuineness": 4.65797233581543, "identity": 0.630874514579773, "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_Intoxication_Altered_States_of_Consciousness/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "02007aa2bb26806552d59a3d71fef489d3a04724b5e21cc745bbd9c51b8b79fa", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "da0dabc0a5ef92205bd148986f857e47c66839ee6af7ee26b5aa28694c30f4ab", "generation_seconds_batch": 24.170163747039624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017115041613578796, "target_z": -0.279296875418598, "ce": 6.38003396987915, "genuineness": 4.68307638168335, "identity": 0.27338001132011414, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/02007aa2bb26806552d59a3d71fef489d3a04724b5e21cc745bbd9c51b8b79fa.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "0272aa849cd464f40ad01eff38982c190f155f55d523daf120380878c284144e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c5d3c9229f3f28b7c15a7f5ede1d7fe812b89a61326626b4d3d7c64825b7c5c9", "generation_seconds_batch": 17.581461039022543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.005698487162590027, "target_z": -0.3203125117207434, "ce": 6.054384231567383, "genuineness": 4.883909225463867, "identity": 0.7807326316833496, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/0272aa849cd464f40ad01eff38982c190f155f55d523daf120380878c284144e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "028b5ac7c49138aa6636b6106d8872df0aba423049f41ac71242ec982e61edb9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "33133ec683843f236cca0d961911116f427438f58517cd8d87e3f6716328cca4", "generation_seconds_batch": 24.44738084601704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01928776502609253, "target_z": -0.27539061286065863, "ce": 6.09409761428833, "genuineness": 4.061748504638672, "identity": 0.3733174800872803, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/028b5ac7c49138aa6636b6106d8872df0aba423049f41ac71242ec982e61edb9.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "02a8cb7494de27b0ecd03f011d9987fb132a194e5d049a38ebbee3cb730477ea", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9413bc938afd06118184d5f62fbebcd036051ee513bcb73e7c61bdf6a2ac70a5", "generation_seconds_batch": 23.661763485055417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.038842201232910156, "target_z": -0.24023438379055753, "ce": 6.062326908111572, "genuineness": 4.65797233581543, "identity": 0.26638174057006836, "hypothesis": "De deur staat nog opa. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/02a8cb7494de27b0ecd03f011d9987fb132a194e5d049a38ebbee3cb730477ea.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "02b210d7e7f3dc6807c620118c482f8df8ae36bbdd6eefe91b97aa1037498768", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ebdbe3bf157f175a26c02f1d42f6d823d71551693e11646cbbba11dec49e3d3b", "generation_seconds_batch": 24.76317036501132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08935786038637161, "target_z": -0.14941406731387674, "ce": 5.959072113037109, "genuineness": 4.7458367347717285, "identity": 0.6652385592460632, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/02b210d7e7f3dc6807c620118c482f8df8ae36bbdd6eefe91b97aa1037498768.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "02c26431d4b2206bad08328a20fc539a39130674a74f7ff0c420052d747c5fcd", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d2afd57cd5c5708fdf9dc4005d30e9879dd341b168e8dee1769fe9fa4afcd72a", "generation_seconds_batch": 25.21574467094615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 6.125868320465088, "genuineness": 4.507347106933594, "identity": 0.5332667827606201, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/02c26431d4b2206bad08328a20fc539a39130674a74f7ff0c420052d747c5fcd.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": "02c84cea07aa610e658b4fe95db3ad84748a7f13533c077749ec52bb2634f3df", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "4434dd288f1d8abb8a3559b6761cb570a4712fb27b04efa3aa400a52887738e9", "generation_seconds_batch": 17.76561112597119, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0002666860818862915, "target_z": -0.3105468687210303, "ce": 6.229123115539551, "genuineness": 4.457139015197754, "identity": 0.27552682161331177, "hypothesis": "someone moved the little blue chair. It used to s stand here beside the tall bookshelf. We can put it back after lunch.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/02c84cea07aa610e658b4fe95db3ad84748a7f13533c077749ec52bb2634f3df.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "02e42e4d28c81917a1bb6059016bd8132a50043a793fe85c0e836f2db838c89d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5651b16e87f0be1a3394dd3d25e0b79fca70ad0355ffaecabc12db637ff2818b", "generation_seconds_batch": 25.1790330929216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03612631559371948, "target_z": -0.2451171785001435, "ce": 6.157639026641846, "genuineness": 4.432034492492676, "identity": 0.5410963892936707, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/02e42e4d28c81917a1bb6059016bd8132a50043a793fe85c0e836f2db838c89d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "03821da8ab77f2bab7d74ec0264b684ea611dc5e54af0214de61cc25354443c8", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9a8a7244493cb331a34adeb8f21b75459d0e7f1540d01ec2dda990fc69b9c1c1", "generation_seconds_batch": 25.29367272905074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007337823510169983, "target_z": -0.2968749899536485, "ce": 6.149696350097656, "genuineness": 4.645420074462891, "identity": 0.6771337985992432, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/03821da8ab77f2bab7d74ec0264b684ea611dc5e54af0214de61cc25354443c8.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "03e222c5556c45ac2a06ffd1153e32cec0c1531a645b860991f7701ebebc6546", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "529c508c6829513c8a23e69cd820df07025224bcb2f4373df5254d6ff3e59f30", "generation_seconds_batch": 25.212551014963537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01438935101032257, "target_z": -0.33593750837195957, "ce": 6.0305562019348145, "genuineness": 4.796044826507568, "identity": 0.5681644678115845, "hypothesis": "Y he encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/03e222c5556c45ac2a06ffd1153e32cec0c1531a645b860991f7701ebebc6546.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "0439a7f446ad54dd70e6800af428d232f6afe4221975bb74ac09c4ed8f81f2ce", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c50c58443d7dd7fcb563dfb9f5cfe7860b644a0399adc37cccec0a0917ef5dca", "generation_seconds_batch": 17.66755737492349, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 6.117925643920898, "genuineness": 4.061748504638672, "identity": 0.2469276636838913, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/0439a7f446ad54dd70e6800af428d232f6afe4221975bb74ac09c4ed8f81f2ce.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "04a263ec343fb46b308869029a5a2498dbe546789110c6af8f78ac65459f0634", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "0b29f099b01afdcf5707cce9af38b7c772c7be662e2e16d8045d00736b8803c6", "generation_seconds_batch": 24.870621656998992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032324060797691345, "target_z": -0.2519531178838344, "ce": 6.022613525390625, "genuineness": 4.243753433227539, "identity": 0.7912240624427795, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/04a263ec343fb46b308869029a5a2498dbe546789110c6af8f78ac65459f0634.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "04cd3bc066e15995350d05a3795fec69a51598e3cbf2a9cb1d86b94dbde19ef0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f5f5e049bb1dddc08c121d7a46c7d930e70b06ebb6098c35735aa827d42394d9", "generation_seconds_batch": 24.648393105948344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 6.062326908111572, "genuineness": 4.344170093536377, "identity": 0.31554919481277466, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/04cd3bc066e15995350d05a3795fec69a51598e3cbf2a9cb1d86b94dbde19ef0.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "04f86a5d7caf62f95afb27231e5f991a7a6d01869bba8deb09b54326444f0b4d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7c176900ea74d750166b0ec7c78530265b61a7fa0517d7e4437bad9049cc3c43", "generation_seconds_batch": 18.521206815959886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033410415053367615, "target_z": -0.25, "ce": 5.990842819213867, "genuineness": 4.381826400756836, "identity": 0.53536456823349, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/04f86a5d7caf62f95afb27231e5f991a7a6d01869bba8deb09b54326444f0b4d.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": "054bda7d58b70dde3ecda691fbd3a54e1b49a3105e69b498811292d81322d5f3", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "156fbdb398eddbf34b2b0fe0e988dba1332391e6c3cfebef7b24e7054309a649", "generation_seconds_batch": 22.41409624903463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.206956148147583, "target_z": 0.06201173392417668, "ce": 5.383228778839111, "genuineness": 4.243753433227539, "identity": 0.29875314235687256, "hypothesis": "De sleutels liggen op de keukentafel. Kijk in de la 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_Intoxication_Altered_States_of_Consciousness/054bda7d58b70dde3ecda691fbd3a54e1b49a3105e69b498811292d81322d5f3.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "058fb16bd4e9353e78d4b8644ee79cd971a0031ab3e7415dff9b0c3a188be4f8", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "fab883bf7216ca962f389f5df2334864e7a6764ba3f99224d247fc2fa580fe36", "generation_seconds_batch": 23.61731172306463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009510532021522522, "target_z": -0.2929687541859798, "ce": 5.935244083404541, "genuineness": 4.883909225463867, "identity": 0.5691178441047668, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/058fb16bd4e9353e78d4b8644ee79cd971a0031ab3e7415dff9b0c3a188be4f8.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "97dbba1d3393b4dc57e356b66be3fbf24ccdad12877b5053914307a12c8fb9c2", "generation_seconds_batch": 19.07643052295316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.316492557525635, "genuineness": 4.419482707977295, "identity": 0.5135916471481323, "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_Intoxication_Altered_States_of_Consciousness/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.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": "059c6c1fd2c94be82769add8e49ffb39d047fe4f14150f5c31fc68161763e8b7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e333d7b395dd75e3891b5fa0f5ad9a1a4dc61e17c679cc60df1309f3c6642028", "generation_seconds_batch": 28.776582426042296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009510532021522522, "target_z": -0.2929687541859798, "ce": 6.125868320465088, "genuineness": 4.8588056564331055, "identity": 0.7857089042663574, "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_Intoxication_Altered_States_of_Consciousness/059c6c1fd2c94be82769add8e49ffb39d047fe4f14150f5c31fc68161763e8b7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "059e85208c9bc9f6ba264e7840d77140db6a72c40503fe88a75b00a25821f73f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "768582d0315870c9303517716cbe21a5e3de12ffd349262e952fc637d58c1355", "generation_seconds_batch": 22.850130185019225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055680759251117706, "target_z": -0.2099609360349071, "ce": 5.760505676269531, "genuineness": 4.6203155517578125, "identity": 0.6659665703773499, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/059e85208c9bc9f6ba264e7840d77140db6a72c40503fe88a75b00a25821f73f.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "065c58f604d6a53c009c5cf1f38c3cbc12e5a82ef2ec0c65b94ab6aee9042058", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "cd631c230427d8ad487e9b9d24daf0a463164abb95602cdc96a6d89d4aaac73d", "generation_seconds_batch": 25.23069732589647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07197613269090652, "target_z": -0.1806640606163091, "ce": 5.681078910827637, "genuineness": 4.796044826507568, "identity": 0.7181874513626099, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/065c58f604d6a53c009c5cf1f38c3cbc12e5a82ef2ec0c65b94ab6aee9042058.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": "06ea90fff2164679c74163db9bbf5719263b04249729ff30185552a930759e87", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cd0dac763ee6e36dd2ffd8340459c61f8ed978621d9233813d2f7581abfb3f43", "generation_seconds_batch": 24.9421005230397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04861942678689957, "target_z": -0.2226562558603717, "ce": 6.133810997009277, "genuineness": 4.7332844734191895, "identity": 0.6329327821731567, "hypothesis": "Escribí el número en el sobre, léelelo bien, y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/06ea90fff2164679c74163db9bbf5719263b04249729ff30185552a930759e87.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "06edfe180579c2d178e4e0a3056f1de1a5f12cbef954a24d8ace1b311df620a0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e2ee3be697349d86e044d3e8f9b3a4d6fdbd8816e70f51f299b676e623cf6770", "generation_seconds_batch": 23.883661767002195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.1894097328186035, "genuineness": 4.162164688110352, "identity": 0.14949581027030945, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/06edfe180579c2d178e4e0a3056f1de1a5f12cbef954a24d8ace1b311df620a0.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "074a6debe6f592be7b7b142525c4f14d850219ea5dc6aaeb4f7459cad99432a1", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3040ecc29d7e959a9cb14dfcdadf4ddafb6913dd633bf8421ad726c706eb1d0c", "generation_seconds_batch": 17.416506941081025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0236331969499588, "target_z": -0.2675781145350506, "ce": 5.935244083404541, "genuineness": 4.532451152801514, "identity": 0.6241459846496582, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/074a6debe6f592be7b7b142525c4f14d850219ea5dc6aaeb4f7459cad99432a1.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "07530e4a4a651e1e0325fe2ab22360dd277323b295b4fae41011b8f07428c4e8", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "03467186a9019bf8f621d541193b25700a66b32f13d2bce729ad3a2110095148", "generation_seconds_batch": 24.350407785037532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0019060224294662476, "target_z": -0.3066406329533616, "ce": 6.062326908111572, "genuineness": 4.7332844734191895, "identity": 0.7268275022506714, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/07530e4a4a651e1e0325fe2ab22360dd277323b295b4fae41011b8f07428c4e8.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "080bbc55c1b4a4ff539eac966cbccd3dfc280778911b63465d33d1aab1603eb0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a5ed73556c8026eb37e8fe1073d15e12f1689b3d03e7a5363bb516c6edaf6d8a", "generation_seconds_batch": 18.364523895084858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.005698487162590027, "target_z": -0.3203125117207434, "ce": 5.982900142669678, "genuineness": 4.7834930419921875, "identity": 0.7213214635848999, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/080bbc55c1b4a4ff539eac966cbccd3dfc280778911b63465d33d1aab1603eb0.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": "0866480cd8bc22560447e3258db0eafb62f2639cc516800a54d43ae78fd49870", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e882261a9f879b858b863c52c6041beef75a9edfab540acfe1a866d6c24a8d53", "generation_seconds_batch": 29.741492870030925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14666326344013214, "target_z": -0.04638671048268995, "ce": 6.046441555023193, "genuineness": 4.406930446624756, "identity": 0.6975822448730469, "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_Intoxication_Altered_States_of_Consciousness/0866480cd8bc22560447e3258db0eafb62f2639cc516800a54d43ae78fd49870.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "097803560cbc239cafd20dd51921fad269d47625b09ea7878ea952a3716abb62", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "50e77fa8eaa93dc113d1410dbf40e7c7bb11ace4775f6612430162099745de33", "generation_seconds_batch": 25.88079219101928, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00516510009765625, "target_z": -0.3007812525115879, "ce": 6.157639026641846, "genuineness": 4.519899368286133, "identity": 0.8099379539489746, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/097803560cbc239cafd20dd51921fad269d47625b09ea7878ea952a3716abb62.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": "09c8fc2d9dcd1d431deb366c880b7e2e6ce9cce07e3de598aa59f56883572923", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "619f277e40f30f4c93110d3f72278e43ff45734c28e08c5b24b9701f86c081be", "generation_seconds_batch": 16.856422004057094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033410415053367615, "target_z": -0.25, "ce": 6.252951145172119, "genuineness": 4.632867813110352, "identity": 0.6001579761505127, "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_Intoxication_Altered_States_of_Consciousness/09c8fc2d9dcd1d431deb366c880b7e2e6ce9cce07e3de598aa59f56883572923.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "09ce7fd245a94b499f31b79ffd5520be11cb79b27288e857328f1f90df403a92", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7eff1c5d75e80d55ba8cc3b8c82f21ed30b294fdb118345592213e987f40884b", "generation_seconds_batch": 16.690037024090998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014942318201065063, "target_z": -0.2832031379765373, "ce": 5.927301406860352, "genuineness": 4.337893962860107, "identity": 0.5908665657043457, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/09ce7fd245a94b499f31b79ffd5520be11cb79b27288e857328f1f90df403a92.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "0acf28f117bc7ba3fb4f4223816dfc853a004ca1adfd70380f633be3244cbb20", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8e12dde9e4001cc9423f1d48732ca4b398e983996b35c88e532035c8c614fe07", "generation_seconds_batch": 32.8548552809516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0062514543533325195, "target_z": -0.2988281346277535, "ce": 6.1020402908325195, "genuineness": 4.507347106933594, "identity": 0.5853873491287231, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/0acf28f117bc7ba3fb4f4223816dfc853a004ca1adfd70380f633be3244cbb20.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": "0b4dc10b4fd3a0b311a424fcc8a92c66534d39399f89ae9a4266fbd06116228b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7f51b596800938129627d388a362737d44376346df9fc5a0cc081623915372ad", "generation_seconds_batch": 18.140902928076684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0475330725312233, "target_z": -0.22460937374420606, "ce": 6.006728172302246, "genuineness": 4.946669578552246, "identity": 0.7736258506774902, "hypothesis": "Tant mon message est arrivé après mon départ, je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "wer": 0.09523809523809523, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/0b4dc10b4fd3a0b311a424fcc8a92c66534d39399f89ae9a4266fbd06116228b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "0bb36a4d02890641272c4295fbd090b1779771ebd33acc64c2ea46e95e3c7dc8", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "59e7c2985cb9a495ea625c3bcd1072f8d099d4766fdca99a2d417698b80fd6c8", "generation_seconds_batch": 22.74046871403698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06056936830282211, "target_z": -0.2011718787673818, "ce": 5.863759994506836, "genuineness": 4.68307638168335, "identity": 0.7367135882377625, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.2, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/0bb36a4d02890641272c4295fbd090b1779771ebd33acc64c2ea46e95e3c7dc8.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": "0c56d911cb0911928da925e27ab49c0a4fb1854281d1b21fed43e0b7cc03777e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dc14ca5e59f584ddd31af207a5a1990818eea3758f95b02191597f401085d0c3", "generation_seconds_batch": 26.593098626006395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.24500846862793, "genuineness": 4.570107460021973, "identity": 0.34473666548728943, "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_Intoxication_Altered_States_of_Consciousness/0c56d911cb0911928da925e27ab49c0a4fb1854281d1b21fed43e0b7cc03777e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "0cb0caf9d4e6cf820c2092150e9da90f384bb32183eff5a4488adb1213d40f6a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a16dcc69e0613ec2475a5a5a6b9c6264197af46490b90b3678fbcb5eced83a6b", "generation_seconds_batch": 25.87343909405172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.046989887952804565, "target_z": -0.22558594608125854, "ce": 5.522225379943848, "genuineness": 4.557555198669434, "identity": 0.5639762878417969, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/0cb0caf9d4e6cf820c2092150e9da90f384bb32183eff5a4488adb1213d40f6a.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "e98692c84c991c8adb7758e6448797f8dbe13060528762e8121340274e1f451d", "generation_seconds_batch": 18.856498042005114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010596886277198792, "target_z": -0.2910156363021454, "ce": 6.149696350097656, "genuineness": 4.162164688110352, "identity": 0.7984434366226196, "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_Intoxication_Altered_States_of_Consciousness/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "0cd2eda0f9a425f1943e88908605ecc9564805fef089f54b5598da1b1c70816d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "91d9ab46be30c65ad6466f86664e3cf3957cbe9b482d890f960a6bf326be3649", "generation_seconds_batch": 27.406480873934925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0040787458419799805, "target_z": -0.3027343703954222, "ce": 6.125868320465088, "genuineness": 4.808597087860107, "identity": 0.7470271587371826, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/0cd2eda0f9a425f1943e88908605ecc9564805fef089f54b5598da1b1c70816d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "0d7256759500425886b8a4b5b14114cc2c2fdc8bddfed824bac1b33543bc1535", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "83060a448ff3cda4026481aec938489f9c421ebe827dae39f33e072239ed60b9", "generation_seconds_batch": 18.72972058400046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.109982967376709, "genuineness": 4.557555198669434, "identity": 0.5850504636764526, "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_Intoxication_Altered_States_of_Consciousness/0d7256759500425886b8a4b5b14114cc2c2fdc8bddfed824bac1b33543bc1535.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "0d852773ed90f62b8910973c9166084949e9475e33e323f986061b15c54624fc", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8a9865bcb2abfe655f862153c95060f3c768296b1a9d4b53001563c1c87be607", "generation_seconds_batch": 21.952454853919335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03721266984939575, "target_z": -0.2431640606163091, "ce": 6.419747352600098, "genuineness": 4.419482707977295, "identity": 0.39696943759918213, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/0d852773ed90f62b8910973c9166084949e9475e33e323f986061b15c54624fc.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "0dbce25506ea51c690f7d52196bb0ad3e0da49a1ba27adbc89e75ffa3c977504", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dbefcf67d0ed6b8b7438e23d9177b501dca40e09a0bc1d141b8fe4c46819560c", "generation_seconds_batch": 24.661910592927597, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.000819668173789978, "target_z": -0.308593750837196, "ce": 5.919358730316162, "genuineness": 4.645420074462891, "identity": 0.6336062550544739, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/0dbce25506ea51c690f7d52196bb0ad3e0da49a1ba27adbc89e75ffa3c977504.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "0df56dc1743ae4b8c33f1d6954fafc6de219b9d98a55eab26f0982e167e692b9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ac10b1e32ab3e6c3129661c28633800b62457b1b4ac07654ca6e3bea749e5c16", "generation_seconds_batch": 23.87242591602262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03503994643688202, "target_z": -0.24707032317424843, "ce": 6.41180419921875, "genuineness": 4.218649387359619, "identity": 0.6612061262130737, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/0df56dc1743ae4b8c33f1d6954fafc6de219b9d98a55eab26f0982e167e692b9.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "0e01eaec6773a31204b00acdd1fb429197fc56a2c9cf0dd308312eaf0792f37a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d03fa7b3584f71dfde2c204fe4dddf0167eab91f128c261e9079d73f5e5d84e6", "generation_seconds_batch": 24.96260817896109, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016028687357902527, "target_z": -0.2812499933024324, "ce": 6.213237762451172, "genuineness": 4.846253395080566, "identity": 0.6678903698921204, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/0e01eaec6773a31204b00acdd1fb429197fc56a2c9cf0dd308312eaf0792f37a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "0e080eb70087508fc2e4c4400efa67fa5975e193c103d36e250947f6ca5791a2", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0ffdad3394c01796b93fc2951780e2e3237e00042254b1022ca0e293e1122348", "generation_seconds_batch": 24.04675851704087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02689225971698761, "target_z": -0.2617187608835474, "ce": 5.967014789581299, "genuineness": 4.507347106933594, "identity": 0.8692963123321533, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/0e080eb70087508fc2e4c4400efa67fa5975e193c103d36e250947f6ca5791a2.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "0e207a8ae12ad71c558373f0b8320a1b97ca4e033224c536b9cfe7c0f72493af", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "wording", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ec0f2fb592c7c9a4effc7dcbd84541942b6382599b6b889cffffa4d7f6f4e3c1", "generation_seconds_batch": 16.534675283008255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03829902410507202, "target_z": -0.2412109427324747, "ce": 6.427689552307129, "genuineness": 4.319066047668457, "identity": 0.5870686173439026, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/0e207a8ae12ad71c558373f0b8320a1b97ca4e033224c536b9cfe7c0f72493af.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": "0e6c91315fb9f4bd4242ebe77eb4ac117e1f91a820223bcc02ae84e478c78270", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "b1ccd6b5c574858adc6b5fd83705c59cb2f78970b46864db57c6493ce1d4a294", "generation_seconds_batch": 19.416652061976492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010596886277198792, "target_z": -0.2910156363021454, "ce": 5.871703147888184, "genuineness": 4.632867813110352, "identity": 0.5330503582954407, "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_Intoxication_Altered_States_of_Consciousness/0e6c91315fb9f4bd4242ebe77eb4ac117e1f91a820223bcc02ae84e478c78270.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "0e8b121cef31e4be247e16bae1b6a2c807faf139c15936052883153b83ed408c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d3e67fa6d3eac233c94d0c7f8fa193e509ffbe35a25a3c7adf05899fdd1c7634", "generation_seconds_batch": 24.584586452925578, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031237691640853882, "target_z": -0.2539062625579393, "ce": 6.022613525390625, "genuineness": 4.570107460021973, "identity": 0.5533600449562073, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/0e8b121cef31e4be247e16bae1b6a2c807faf139c15936052883153b83ed408c.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "0eada5c6a8e5ef9c4faab2cf75e0efbd514d8f1708203538b251ad5ae9cb9c57", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b9fbcf4f517485c0eddfe53fece2f73fb933a404fb009473bc1a66ec243ea94b", "generation_seconds_batch": 17.94801777903922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.133810997009277, "genuineness": 4.595211505889893, "identity": 0.5065695643424988, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/0eada5c6a8e5ef9c4faab2cf75e0efbd514d8f1708203538b251ad5ae9cb9c57.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "0f1c1c3d8af42ceffe99b1ee80fd44d19ef115c7a46fddab8cb86422018ab07e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "49dfa3376aa6e12fa79c28d5f127dc499a97c9134933595fde93c4bc335e2814", "generation_seconds_batch": 28.337117122020572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.051335327327251434, "target_z": -0.21777343436051516, "ce": 6.133810997009277, "genuineness": 4.469690799713135, "identity": 0.7934561967849731, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/0f1c1c3d8af42ceffe99b1ee80fd44d19ef115c7a46fddab8cb86422018ab07e.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": "0f6ccefac4941878b8b217ef07a3fa9d513413421f53242e6f1a5f126dc2c172", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9fcdaf882b76d8183819d0ad3b54f7c7982a457518e92618b994c8ab4c0002fc", "generation_seconds_batch": 16.86969774402678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008424177765846252, "target_z": -0.2949218720698142, "ce": 6.197352409362793, "genuineness": 4.6705241203308105, "identity": 0.6039704084396362, "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_Intoxication_Altered_States_of_Consciousness/0f6ccefac4941878b8b217ef07a3fa9d513413421f53242e6f1a5f126dc2c172.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "0fa8ab8cd56156850631803155b5709ac87edcc0d9140c798d35f26e8288d3a2", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "babf02adce2057559ee92fb31ff1359ca56011e09095c3d88999cdaa4a0c934d", "generation_seconds_batch": 24.903705191914923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031237691640853882, "target_z": -0.2539062625579393, "ce": 5.831989288330078, "genuineness": 4.557555198669434, "identity": 0.5851849317550659, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/0fa8ab8cd56156850631803155b5709ac87edcc0d9140c798d35f26e8288d3a2.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "103408facc44ee6699d944d8da9b594cb840b3eff24cd07c05da23425f19272e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f7c12c8677f0ac76b772da59e3bf473e9d79b04d30eaa1f451d17e7810dfff2a", "generation_seconds_batch": 25.97859326703474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06763070076704025, "target_z": -0.1884765589419172, "ce": 6.2767791748046875, "genuineness": 4.7332844734191895, "identity": 0.8369388580322266, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. J'ai un émaçant.", "wer": 0.16666666666666666, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/103408facc44ee6699d944d8da9b594cb840b3eff24cd07c05da23425f19272e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "10570892b3a667be75e6842e695f4ef69e8462da22429df6e594965e4b515937", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a8b215834cc18a812204e68d91edb273f3eff153713ba1bc0209a93e149ed601", "generation_seconds_batch": 17.403280145023018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02580590546131134, "target_z": -0.2636718787673818, "ce": 6.054384231567383, "genuineness": 4.469690799713135, "identity": 0.47126883268356323, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/10570892b3a667be75e6842e695f4ef69e8462da22429df6e594965e4b515937.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "10a49fa06ffa5f6e461100ac051e2cf48288ccac8186192e32549b9b6ac2aa69", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9ab08e3fc31b4302aa055753e28b99b8ffe37b2a4c202ccdbe56915364bdec21", "generation_seconds_batch": 23.544562345021404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.046989887952804565, "target_z": -0.22558594608125854, "ce": 6.181467056274414, "genuineness": 4.7081804275512695, "identity": 0.5339481830596924, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/10a49fa06ffa5f6e461100ac051e2cf48288ccac8186192e32549b9b6ac2aa69.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "10a5c149ac007f8193fbec6b535aa6bce4a5aa1f88a7aced1659609faca824f9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "wording", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "febf94abecd386bbb30d9110f65c88ff21f87d80058edfed99346d7042bbe5ef", "generation_seconds_batch": 17.23828439495992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007337823510169983, "target_z": -0.2968749899536485, "ce": 6.054384231567383, "genuineness": 4.720732688903809, "identity": 0.6140459775924683, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/10a5c149ac007f8193fbec6b535aa6bce4a5aa1f88a7aced1659609faca824f9.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "1153d388f0fcad94f6c3ac75b06ee7d6e1497429b7410f17281c7868624ab615", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0d59c5e8db69bcd624af91e3718077eebb5807c255f4c8c7ba15c319e90c9e2e", "generation_seconds_batch": 30.85701534303371, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 5.34748649597168, "genuineness": 4.457139015197754, "identity": 0.5333719253540039, "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_Intoxication_Altered_States_of_Consciousness/1153d388f0fcad94f6c3ac75b06ee7d6e1497429b7410f17281c7868624ab615.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "11be2b740dffc791d6c9239c3849d9b71f7b9a6cb6c14980b5ad59e79d01d207", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1b6c5a148abea7fdec7926db527f58fd20b30bea1aa31bb72a84b7f055e06fe8", "generation_seconds_batch": 23.834383687004447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 6.0305562019348145, "genuineness": 4.482243061065674, "identity": 0.7009352445602417, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/11be2b740dffc791d6c9239c3849d9b71f7b9a6cb6c14980b5ad59e79d01d207.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "11beec733916ef7db660d79f76f5f361b53507b511fdbf67b461078690310a7b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "133ee1dd2869f800295ceeaed45ff694a4f5cce07c5a662ce6514fd6ed2f7398", "generation_seconds_batch": 17.3182741869241, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2506820559501648, "target_z": 0.1406249966512162, "ce": 5.9431867599487305, "genuineness": 4.375550270080566, "identity": 0.6349775195121765, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/11beec733916ef7db660d79f76f5f361b53507b511fdbf67b461078690310a7b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "11dd3b89e84e1f2da55c32cf4c5ef1794eb571a2d999f7685f59ac71fcbc5815", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1aaef665d165e9cf7c3653292135fbc62f2a701ba31b0f1fa0e7275f4186415b", "generation_seconds_batch": 27.406480873934925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011683255434036255, "target_z": -0.28906249162804043, "ce": 6.09409761428833, "genuineness": 4.959221839904785, "identity": 0.7815091013908386, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/11dd3b89e84e1f2da55c32cf4c5ef1794eb571a2d999f7685f59ac71fcbc5815.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "3c8c02ca7729880cf530440d1c8b0559d15a25f08f2c05525b221d8481af03f1", "generation_seconds_batch": 21.070181149989367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06926023960113525, "target_z": -0.18554686872103035, "ce": 6.300607204437256, "genuineness": 4.268857479095459, "identity": 0.6808176040649414, "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_Intoxication_Altered_States_of_Consciousness/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": "12cf9728f10bf00a03cb97177cf360ac2b0881098c23b570b22deae464b8d8ed", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6269f4b0b27a7d014fdd59f6e9d0fd92fc4fc21c46874e8f105a77d6012d7146", "generation_seconds_batch": 16.857233191025443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04210127890110016, "target_z": -0.2343750033487838, "ce": 6.109982967376709, "genuineness": 4.3504462242126465, "identity": 0.4608228802680969, "hypothesis": "Your message arrived after I had left. I f read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.043478260869565216, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/12cf9728f10bf00a03cb97177cf360ac2b0881098c23b570b22deae464b8d8ed.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "136e5d5dfbdc152215bbf71953fa499c0c7d0296aa062ce4b1b47db249b642fb", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "bc583bb7dfd6c37ffa7be8979d88a0f9dd8ecf9181f926a653ff336b2039073c", "generation_seconds_batch": 18.55442853202112, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03666949272155762, "target_z": -0.2441406195582263, "ce": 6.316492557525635, "genuineness": 4.68307638168335, "identity": 0.41357457637786865, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/136e5d5dfbdc152215bbf71953fa499c0c7d0296aa062ce4b1b47db249b642fb.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "1387b12ed1c8b5ae998b2404b98f6654515b0ac1064a6e6d21799cb98e50543f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "48f0652f1a8dc3204ce997f5088af81bd6618cc46114c63d91141f3f6494c3c0", "generation_seconds_batch": 17.732315327972174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032324060797691345, "target_z": -0.2519531178838344, "ce": 6.260893821716309, "genuineness": 4.457139015197754, "identity": 0.7621171474456787, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/1387b12ed1c8b5ae998b2404b98f6654515b0ac1064a6e6d21799cb98e50543f.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": "13a546cd5c3cd2ae476fbb509f3dae829450629d7cfff167a0a2e11fd303a16f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ef4f7db856760a8de2048b9687e1b52a99bc639a199deae25d77c1db774783b1", "generation_seconds_batch": 17.76561112597119, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.403861999511719, "genuineness": 4.65797233581543, "identity": 0.32626232504844666, "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_Intoxication_Altered_States_of_Consciousness/13a546cd5c3cd2ae476fbb509f3dae829450629d7cfff167a0a2e11fd303a16f.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": "13c2092dedbeaab0626697ad7e57e36d72e357a59bbb46a43b12d14a3b98ebb1", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "6b1c56215505e347fdaf2d10102e16eaf5d4c3bd275eedbf9c5a65a2ab719d00", "generation_seconds_batch": 17.424085525097325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.059483014047145844, "target_z": -0.2031249966512162, "ce": 5.911416053771973, "genuineness": 4.595211505889893, "identity": 0.6683726906776428, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous 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_Intoxication_Altered_States_of_Consciousness/13c2092dedbeaab0626697ad7e57e36d72e357a59bbb46a43b12d14a3b98ebb1.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "13e69c97d0a5028148a9297cf1fc8e936d3e7ee8534cde7b750684463b26cbbd", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "e94ed9c62ebca222b0b8c2d846b1ed2d72223b6bf4b30f2fe727e79d0548b822", "generation_seconds_batch": 25.355016073095612, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0507921427488327, "target_z": -0.21875000669756764, "ce": 5.77639102935791, "genuineness": 4.607763767242432, "identity": 0.5995029211044312, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/13e69c97d0a5028148a9297cf1fc8e936d3e7ee8534cde7b750684463b26cbbd.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "141d7c273bc90adde0a04ffb8c911d71eceaa02f2029f9c54e2f2abd352aa565", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ede82ce233807012e65501d72e6c8db3847f332c3f6b001ff153a029fba69de1", "generation_seconds_batch": 16.68350203090813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1075543612241745, "target_z": -0.11669922220343332, "ce": 5.998785495758057, "genuineness": 4.055472373962402, "identity": 0.5980124473571777, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/141d7c273bc90adde0a04ffb8c911d71eceaa02f2029f9c54e2f2abd352aa565.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "141d8b55a6023ce2c20ff0bf2750f0dbf90c08d618b21ab295cb43aec82f3bb9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c5890be10f309356f27bdca04973ffeb925016e46f7228dd9187073df885edac", "generation_seconds_batch": 23.887682396103628, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03775584697723389, "target_z": -0.2421875016743919, "ce": 6.205295085906982, "genuineness": 4.432034492492676, "identity": 0.6486537456512451, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/141d8b55a6023ce2c20ff0bf2750f0dbf90c08d618b21ab295cb43aec82f3bb9.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": "146d941b61e80165198aedfe818440d481a0116d03e6290ffeb296df60896791", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "b62cecdc1689296464d89fe8ae3b7e1f0336f56543406c1215abdc9db31e89ed", "generation_seconds_batch": 15.999899087008089, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0507921427488327, "target_z": -0.21875000669756764, "ce": 6.09409761428833, "genuineness": 4.243753433227539, "identity": 0.538569986820221, "hypothesis": "Ik schreef het nummer op de enveloop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/146d941b61e80165198aedfe818440d481a0116d03e6290ffeb296df60896791.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "1495386f1ed4de80f5e762268cc7cbcc290f91f19bad885d2723ae7f77611098", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f5747537e78914c9627887de668656e01d875260ebf6f2dff0e8668b709ea654", "generation_seconds_batch": 22.845336099970154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06437162309885025, "target_z": -0.1943359393836909, "ce": 6.252951145172119, "genuineness": 4.871357440948486, "identity": 0.7390557527542114, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/1495386f1ed4de80f5e762268cc7cbcc290f91f19bad885d2723ae7f77611098.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "14b319e24f5f897ae072efb961e587b8d62ae3c1e51d9ce6e9958e72d2595507", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "49301cf0a57e438c782a10bedf3e0e3e19ee6001cde9c6eee315bd1d9c097ca0", "generation_seconds_batch": 17.66755737492349, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01928776502609253, "target_z": -0.27539061286065863, "ce": 6.24500846862793, "genuineness": 4.325342178344727, "identity": 0.1598113626241684, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/14b319e24f5f897ae072efb961e587b8d62ae3c1e51d9ce6e9958e72d2595507.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "14ff5b0df5c90c28458561406181a93da06a0af9d2d03c2de73709a13aae02d6", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ca8e19e859e26f8eaf16aebb8efd8af36cc9bde6c7e478c193250987d41da0ed", "generation_seconds_batch": 25.25761707802303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04427400231361389, "target_z": -0.2304687407908445, "ce": 5.911416053771973, "genuineness": 4.6956281661987305, "identity": 0.570315957069397, "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_Intoxication_Altered_States_of_Consciousness/14ff5b0df5c90c28458561406181a93da06a0af9d2d03c2de73709a13aae02d6.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "15008e0302c1f3f0d82a5c952b53943c340cdb6e0943df1f323697602e2817b6", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "73ae9c13dcc36d87460941d8d0321f5487d06586c129a7f6ce5b0e5f904918b6", "generation_seconds_batch": 23.881106097018346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 6.221180438995361, "genuineness": 4.444586753845215, "identity": 0.4198998212814331, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/15008e0302c1f3f0d82a5c952b53943c340cdb6e0943df1f323697602e2817b6.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "154664ff04c5dcb575e77b779f43a764483b79b1d7a54ec367a871d52e3bb406", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "db17805bcb36b5db40c61de773aa7420b022f5f833a7b4a0badc0a5562c9eebf", "generation_seconds_batch": 17.575008946005255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010596886277198792, "target_z": -0.2910156363021454, "ce": 6.157639026641846, "genuineness": 4.883909225463867, "identity": 0.7308036684989929, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/154664ff04c5dcb575e77b779f43a764483b79b1d7a54ec367a871d52e3bb406.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "15571e8d1f85dd81a17484b5732751a37e442e43b0a63ecdf2ce1bab54cd89d5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6ac23b116473f19b2221acc770ff17df3fcb0dc31e2a9688ded54f3ebe68abdf", "generation_seconds_batch": 22.943109089974314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 6.23706579208374, "genuineness": 4.419482707977295, "identity": 0.5679411888122559, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/15571e8d1f85dd81a17484b5732751a37e442e43b0a63ecdf2ce1bab54cd89d5.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "7f00014b0b08cfef928c71de7cf6f5b12b04ff070252ac6a9269d4b677ebd91f", "generation_seconds_batch": 17.116291019017808, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0040787458419799805, "target_z": -0.3027343703954222, "ce": 6.300607204437256, "genuineness": 4.306513786315918, "identity": 0.6948369741439819, "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_Intoxication_Altered_States_of_Consciousness/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "15623a33935a2b0e7a66b888e9c433a71c580236bdfd852a3b9a353c48bb9792", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "32dcc83925452c2e2a4fd2b37bf2928c8131d55ac37829c026dd004311012d67", "generation_seconds_batch": 22.554779938072897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013855963945388794, "target_z": -0.2851562558603717, "ce": 5.974957466125488, "genuineness": 4.770940780639648, "identity": 0.7073521614074707, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/15623a33935a2b0e7a66b888e9c433a71c580236bdfd852a3b9a353c48bb9792.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "16629f00df2375b28964e09f7b38b0681ad7e0a669a2d74e9354a2286b3a90ff", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "63ca1c8a755a73a82690807dc2ec8373633ecb241c86cabb547de236fd658894", "generation_seconds_batch": 25.24216433498077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0062514543533325195, "target_z": -0.2988281346277535, "ce": 6.078212261199951, "genuineness": 4.645420074462891, "identity": 0.7473640441894531, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/16629f00df2375b28964e09f7b38b0681ad7e0a669a2d74e9354a2286b3a90ff.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": "172d2eb75d1c32b272fbfb87df303c496fc141a1aba9a7fd49e6b9d4cdb5590d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "77dcb2ea772af2aed8bf4795adc6bb2e197ea6cd9b8d9559d9065f5150fd6bda", "generation_seconds_batch": 18.73995905998163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05839665234088898, "target_z": -0.20507812793018584, "ce": 6.006728172302246, "genuineness": 4.796044826507568, "identity": 0.7023230195045471, "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_Intoxication_Altered_States_of_Consciousness/172d2eb75d1c32b272fbfb87df303c496fc141a1aba9a7fd49e6b9d4cdb5590d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "177006f8bf7857d6bd39d21c3ed1a06440ec379704339c30bb651b8ea0e0d9b9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8edfde00e7482ea238606db4355b0825f4cc86fc72767e4eb68f72fef4a0d5b2", "generation_seconds_batch": 24.442077224957757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0024394094944000244, "target_z": -0.3144531312789697, "ce": 5.998785495758057, "genuineness": 4.645420074462891, "identity": 0.6658081412315369, "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_Intoxication_Altered_States_of_Consciousness/177006f8bf7857d6bd39d21c3ed1a06440ec379704339c30bb651b8ea0e0d9b9.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "17a9b420994e1315ea04af7de789a6b0ca5cd823535fdb64aeb54b42ef4ff8fc", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7cf5c3c8e6853414993061eff8cc6a9d77138c4353f9b776a7a200356f5d9e51", "generation_seconds_batch": 22.868231364060193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03775584697723389, "target_z": -0.2421875016743919, "ce": 5.7684478759765625, "genuineness": 4.7332844734191895, "identity": 0.6861867308616638, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/17a9b420994e1315ea04af7de789a6b0ca5cd823535fdb64aeb54b42ef4ff8fc.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "17b39a0b86eddfa21ae13b3ed951ee35bab644b1ca7e310c05b4c14a1802c186", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "04d6d007de12ec14c1bd554f25e0097c31e3d19c711c4918585979b433c8add2", "generation_seconds_batch": 24.352556733996607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012769609689712524, "target_z": -0.2871093737442061, "ce": 6.0305562019348145, "genuineness": 4.482243061065674, "identity": 0.5216273665428162, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/17b39a0b86eddfa21ae13b3ed951ee35bab644b1ca7e310c05b4c14a1802c186.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "17ec91365eeaa924103b29c7e0cac041bc4424dee4ea5d4da1e3212b28886478", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3abbd299fbb3039fc10e5c910ee3a0b61ce04b2d87c85463864e9b483ce8af97", "generation_seconds_batch": 23.933620670926757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.046441555023193, "genuineness": 4.557555198669434, "identity": 0.7976728677749634, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/17ec91365eeaa924103b29c7e0cac041bc4424dee4ea5d4da1e3212b28886478.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "1819aff5a9bd4d6c7cc4500be323793d6a14c887655bdbd43c2bc5af0c627e02", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "cf000cbaf57a11d92def6b0763cacea57af01c6413328803f7c7234312cd34e4", "generation_seconds_batch": 24.233384798048064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.000819668173789978, "target_z": -0.308593750837196, "ce": 6.149696350097656, "genuineness": 4.68307638168335, "identity": 0.5026832818984985, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/1819aff5a9bd4d6c7cc4500be323793d6a14c887655bdbd43c2bc5af0c627e02.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "181eecc5861143c7c6638470a596fa0deac3ea4ce232b74a591fe9cdd36b6e10", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "56f3749c4930891cbf1a058e62646f62a5e2ded4e1291aaee98afb592943418a", "generation_seconds_batch": 18.164981956011616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1108134388923645, "target_z": -0.1108398417616596, "ce": 5.804190158843994, "genuineness": 4.6203155517578125, "identity": 0.576121985912323, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/181eecc5861143c7c6638470a596fa0deac3ea4ce232b74a591fe9cdd36b6e10.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "184b5b50204914854b76a13c7357342fa48c2433e24620bd7c3fc730d05db596", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "83bc48d910980aa2c17639f964bf59c3a0d86dbc92b0732c5e7614bfb5b6466f", "generation_seconds_batch": 22.54671673499979, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09478965401649475, "target_z": -0.139648437709299, "ce": 6.078212261199951, "genuineness": 4.557555198669434, "identity": 0.7360806465148926, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Quand tu es prêté un jeté pour que tu sors, dis-moi quand tu es prêt.", "wer": 0.8888888888888888, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/184b5b50204914854b76a13c7357342fa48c2433e24620bd7c3fc730d05db596.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "186a07d8e2309cafdfb64842d9e9010c77422abd88d8833fbd2745812b1c552f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "59761687da1b629909ed60f2b2e20fb34fd901840bf0c55684a527fa8443d9b5", "generation_seconds_batch": 27.677895978093147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2604592740535736, "target_z": 0.15820311118626676, "ce": 5.847874641418457, "genuineness": 4.281409740447998, "identity": 0.6887487173080444, "hypothesis": "Ik heb het eh kleine 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_Intoxication_Altered_States_of_Consciousness/186a07d8e2309cafdfb64842d9e9010c77422abd88d8833fbd2745812b1c552f.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "18c216e48d0cdbd9529a5d36519d5424cc1688fd9940d596f47c4f34e90e2e0c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "cf7d0d83f0e2b1dfd77bbc4fca098bb3e3c628a31724d3dd40913a53108195bd", "generation_seconds_batch": 18.936011858982965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09098739922046661, "target_z": -0.1464843770929899, "ce": 6.078212261199951, "genuineness": 4.362998008728027, "identity": 0.6084439158439636, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/18c216e48d0cdbd9529a5d36519d5424cc1688fd9940d596f47c4f34e90e2e0c.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "18c34505f52568a55913239d354b57fee04fa67b4a69c4bab09c8c27f8c42bdf", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c414ca9abccf201cd7df9cc1f67e18696cf046dad69724b9c36f368dda453be2", "generation_seconds_batch": 24.906401372049004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04970578849315643, "target_z": -0.220703124581402, "ce": 6.23706579208374, "genuineness": 4.7081804275512695, "identity": 0.41527149081230164, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/18c34505f52568a55913239d354b57fee04fa67b4a69c4bab09c8c27f8c42bdf.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "18f0d66a5fe7289552fefc594a24744dee5f11a2c91a2c58c5182ebd93330451", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "87856e7ae87ad4271c3bd40b90ecf70d207c4c60c7bfd4fe1ad3c28c991e02f8", "generation_seconds_batch": 23.780435819062404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033410415053367615, "target_z": -0.25, "ce": 6.403861999511719, "genuineness": 4.444586753845215, "identity": 0.6742855310440063, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/18f0d66a5fe7289552fefc594a24744dee5f11a2c91a2c58c5182ebd93330451.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "190045e4f8ee49dc8c173b18375d69c9f20fc33195a5d689f7751985e0d177a6", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "784ed35234b7c7d482d78f7310fba9a427b2efacb603e63ffa228d5110209c68", "generation_seconds_batch": 25.089299214072526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 6.316492557525635, "genuineness": 4.243753433227539, "identity": 0.5669558644294739, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/190045e4f8ee49dc8c173b18375d69c9f20fc33195a5d689f7751985e0d177a6.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": "1931c16ec4b7db47e06cf2b99f7b77e2c46db0a5249a4cb24ab164e0fb86a062", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "442da12674a3da6f91d5dbaad5c9e56d90085d6b4a1e901a592aedb017550451", "generation_seconds_batch": 19.416652061976492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 6.006728172302246, "genuineness": 4.645420074462891, "identity": 0.668574869632721, "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_Intoxication_Altered_States_of_Consciousness/1931c16ec4b7db47e06cf2b99f7b77e2c46db0a5249a4cb24ab164e0fb86a062.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": "1a4a74faf63bb8869f6014e6fbb5a3d6386a2289c6ed4b272ff8528a4c4ba701", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "9f4751b87e1c2afc0b2a82b541b552611eaed2dc0b24272219850c7f739ca770", "generation_seconds_batch": 16.856422004057094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06491480022668839, "target_z": -0.1933593804417737, "ce": 5.990842819213867, "genuineness": 4.419482707977295, "identity": 0.5196056365966797, "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_Intoxication_Altered_States_of_Consciousness/1a4a74faf63bb8869f6014e6fbb5a3d6386a2289c6ed4b272ff8528a4c4ba701.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "1a9e6a46f84111d5436e1514a71e871e3bc3ba64c907001346ce6073111eb32b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7265e3cfc1c2c161ce4a8eab551ed128fedea552e348913335851ec6788a5872", "generation_seconds_batch": 24.981380708049983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.001353040337562561, "target_z": -0.3124999866048647, "ce": 6.141753673553467, "genuineness": 4.469690799713135, "identity": 0.6133022904396057, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/1a9e6a46f84111d5436e1514a71e871e3bc3ba64c907001346ce6073111eb32b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "1aa060f019503009e971eb3a7dbd6dd63b86e2ee251ccf648b53bd195f461f31", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fd275d4f359bea7e546f97c58079a63f52ac6f1a1a535d00fb4a8d4fd7a3a39c", "generation_seconds_batch": 24.135887932032347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003525763750076294, "target_z": -0.316406249162804, "ce": 6.038498878479004, "genuineness": 4.3127899169921875, "identity": 0.7762503623962402, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/1aa060f019503009e971eb3a7dbd6dd63b86e2ee251ccf648b53bd195f461f31.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "1c253c8fe9b8317908b9c06fd7330b8419a54ffb3527fe37459e575d16c6d0cb", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a893aa70521ae1046add83314b4e69737738f373571af8283dce6ea7f4ff4d52", "generation_seconds_batch": 22.93600436602719, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02689225971698761, "target_z": -0.2617187608835474, "ce": 6.229123115539551, "genuineness": 4.18726921081543, "identity": 0.3022783100605011, "hypothesis": "The door is still open. I've put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/1c253c8fe9b8317908b9c06fd7330b8419a54ffb3527fe37459e575d16c6d0cb.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "1cad3c9c270b6bc0c9dac46d0cba68a5432cf0c6bae9a428a33b0cb598974dd5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "fd2b07bbfe1ef22fe89018651a006d4a678b771bcca05c02ab55b258af839bad", "generation_seconds_batch": 24.201847578049637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04807624965906143, "target_z": -0.2236328148022889, "ce": 5.935244083404541, "genuineness": 4.143336772918701, "identity": 0.5125387907028198, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/1cad3c9c270b6bc0c9dac46d0cba68a5432cf0c6bae9a428a33b0cb598974dd5.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "1cf91de57e4f36a3227df1927e488459b7076f8725165eabd03e6ee1de350776", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ae61ed8eae242b54f0411f8349922a63df54e1c77ba2927fe909aa36a1cda78f", "generation_seconds_batch": 27.015567269991152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.41180419921875, "genuineness": 4.293961524963379, "identity": 0.4739564061164856, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/1cf91de57e4f36a3227df1927e488459b7076f8725165eabd03e6ee1de350776.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "1cfbef95c60b9a3806514eedf2ae828e14731b59938d22df0bb7b27520350049", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "88d26b20d42fd67aa8bd73f5cc23b15b514feca00eaeb7be23bfce98a3db977b", "generation_seconds_batch": 25.244485217961483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04536035656929016, "target_z": -0.2285156229070101, "ce": 6.229123115539551, "genuineness": 4.519899368286133, "identity": 0.33654987812042236, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/1cfbef95c60b9a3806514eedf2ae828e14731b59938d22df0bb7b27520350049.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "f480398697d475fa1eb57b111b017a758e3c57f7dc4fd13f14851932ca5f6b21", "generation_seconds_batch": 18.419146169093437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013855963945388794, "target_z": -0.2851562558603717, "ce": 6.332377910614014, "genuineness": 4.507347106933594, "identity": 0.632729172706604, "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_Intoxication_Altered_States_of_Consciousness/1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "1d80641337989217f0491675a25bfa3fed0f3ab63a09dafaceda82d3216b3662", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "daae2227badd52de1d8705e440abb02acf0620a08c039cc4cc1ef225941415b5", "generation_seconds_batch": 23.183982342015952, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011683255434036255, "target_z": -0.28906249162804043, "ce": 6.038498878479004, "genuineness": 4.325342178344727, "identity": 0.563654363155365, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/1d80641337989217f0491675a25bfa3fed0f3ab63a09dafaceda82d3216b3662.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "b18989f123df5fe9b26aedfaebb97f12ddd18bcbd185f5bf5715935f9c76e502", "generation_seconds_batch": 17.993259836919606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009510532021522522, "target_z": -0.2929687541859798, "ce": 6.24500846862793, "genuineness": 4.162164688110352, "identity": 0.429703950881958, "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_Intoxication_Altered_States_of_Consciousness/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "1db11c965640db60bee4dccf9776c281da04d70425ba0fb9b3094be3627ac393", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5007ab482ee329eafeb42f29b3cf8bf57d987b96cda87eb566e9a2373bddf038", "generation_seconds_batch": 18.408938145032153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007337823510169983, "target_z": -0.2968749899536485, "ce": 6.046441555023193, "genuineness": 4.595211505889893, "identity": 0.6462857723236084, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/1db11c965640db60bee4dccf9776c281da04d70425ba0fb9b3094be3627ac393.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "1e8df6763a4dc6905185ed578b68075f7d41a3b8c4cb09fdb76990916a915755", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0b1d6b74e0429b6509f07e04579b2b1cef1688a8cc3923ecbbbc602b559bf8ee", "generation_seconds_batch": 17.94801777903922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03503994643688202, "target_z": -0.24707032317424843, "ce": 6.109982967376709, "genuineness": 4.457139015197754, "identity": 0.6834185123443604, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/1e8df6763a4dc6905185ed578b68075f7d41a3b8c4cb09fdb76990916a915755.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "1e9625b23312ce31d15196cb48479b728267e345c213b25fe3947646e1404675", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "35d9c3753b9845f38b6ae8ed329f98e1780f85cac89a5914d362a9ad74d64db3", "generation_seconds_batch": 23.979394952999428, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06382844597101212, "target_z": -0.1953124983256081, "ce": 5.990842819213867, "genuineness": 4.494794845581055, "identity": 0.3748476803302765, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/1e9625b23312ce31d15196cb48479b728267e345c213b25fe3947646e1404675.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "d2a7800c1bbcb3d215b2445ffa1f882605c96aac5355bf00eb85ad202884fe6a", "generation_seconds_batch": 18.419146169093437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013855963945388794, "target_z": -0.2851562558603717, "ce": 6.300607204437256, "genuineness": 4.607763767242432, "identity": 0.7454746961593628, "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_Intoxication_Altered_States_of_Consciousness/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "1ecad71728bd4a781a9da07ed0ea9d8fc78666d5325b9e6392473924573a9486", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5fcb75f2cbc96c9638126e5ec4b23ba2e50f9169c06fe657ef44b1054e1029dc", "generation_seconds_batch": 25.544484158977866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031237691640853882, "target_z": -0.2539062625579393, "ce": 6.292664527893066, "genuineness": 4.545003414154053, "identity": 0.3585692048072815, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/1ecad71728bd4a781a9da07ed0ea9d8fc78666d5325b9e6392473924573a9486.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "1ef721b9dddab4d211d6deeaea928b9d0c7975bd372df2373f53905aeb02404e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3943d0ca9d7f7c6a12b30806b2ada14e67576a3134efe952b24b5c865c1c076b", "generation_seconds_batch": 23.277833850006573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 6.038498878479004, "genuineness": 4.519899368286133, "identity": 0.6126830577850342, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime, 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_Intoxication_Altered_States_of_Consciousness/1ef721b9dddab4d211d6deeaea928b9d0c7975bd372df2373f53905aeb02404e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "1f040383f9253ec236ef6a6c17b1ed89811a9b953546da44b36cb4a4ce409106", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "b63c08fce1edaa653a7d0b70c06ebb20ffbeca7a2be012f63e28a89ef4f49c13", "generation_seconds_batch": 24.661910592927597, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011683255434036255, "target_z": -0.28906249162804043, "ce": 5.927301406860352, "genuineness": 4.632867813110352, "identity": 0.7578604221343994, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/1f040383f9253ec236ef6a6c17b1ed89811a9b953546da44b36cb4a4ce409106.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "1f5e3b151ca0eaee18ab0974bde4222df02d35f79f2f4dd1f5ab4f6edf2c2a7c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "623c0d6c907bcde25b61a783bc19faf40673b3253bbc564fc79232c9c906a23b", "generation_seconds_batch": 22.468945603002794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031237691640853882, "target_z": -0.2539062625579393, "ce": 6.229123115539551, "genuineness": 4.883909225463867, "identity": 0.5433602333068848, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/1f5e3b151ca0eaee18ab0974bde4222df02d35f79f2f4dd1f5ab4f6edf2c2a7c.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "1f63078daef78c3698609b737926036039b4618a27224c93ed2f8797c6284057", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "558b79f80c5330a996ce551fd6ec04c244bdc19d1548b48f2afe3dd447a613b2", "generation_seconds_batch": 24.044635790982284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02580590546131134, "target_z": -0.2636718787673818, "ce": 6.459460258483887, "genuineness": 4.432034492492676, "identity": 0.5686078667640686, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/1f63078daef78c3698609b737926036039b4618a27224c93ed2f8797c6284057.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "1f6c48f86647b7ac88b65848551b603c8cbc7694f00c46e4ca1d4bef7f7dd4a6", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "581470c9178ae1208f99d3272f6e6378d226b84fbeed2653a56cebad4e444b50", "generation_seconds_batch": 24.135887932032347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012769609689712524, "target_z": -0.2871093737442061, "ce": 6.09409761428833, "genuineness": 4.432034492492676, "identity": 0.7815554141998291, "hypothesis": "J'ai trouvé j'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/1f6c48f86647b7ac88b65848551b603c8cbc7694f00c46e4ca1d4bef7f7dd4a6.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "1fdee323904fae4967b9c524fde5d4b701fbd16a7dbf9b07c493078101b38239", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "dd4d65880814effda081fc8acfba2ddad464581d1a6d8438514ff2de3483f57b", "generation_seconds_batch": 18.40033161395695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031237691640853882, "target_z": -0.2539062625579393, "ce": 6.062326908111572, "genuineness": 4.7332844734191895, "identity": 0.6027025580406189, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/1fdee323904fae4967b9c524fde5d4b701fbd16a7dbf9b07c493078101b38239.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": "1ffaa26510a7032ba16ba4fe2e9648dfba565113a117a14f928b73e427418f6e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "35d64477c05081163dc65d20a78aa7923d0b6cf0d4ec74452aa7a781a9cd8750", "generation_seconds_batch": 16.29145611997228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.038842201232910156, "target_z": -0.24023438379055753, "ce": 6.070269584655762, "genuineness": 4.394378662109375, "identity": 0.2838585376739502, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het het stond hier naast de hoge boekenkast. We zetten het na de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/1ffaa26510a7032ba16ba4fe2e9648dfba565113a117a14f928b73e427418f6e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "200a7cf5c081d4c1cf48405257c1c9feb049908ee1f763c92affb7f6e9586ac1", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "243a235c644e26cf9e0453f5849d2341af0276e7eec08bc938c1beee48463d58", "generation_seconds_batch": 17.563004769966938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014942318201065063, "target_z": -0.2832031379765373, "ce": 6.229123115539551, "genuineness": 4.6203155517578125, "identity": 0.47077369689941406, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/200a7cf5c081d4c1cf48405257c1c9feb049908ee1f763c92affb7f6e9586ac1.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "2026d158e8f81271f97218efb55da8686b08fd99528708e9e0e18c16bb5eddaf", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "wording", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "5038dd2da85e4d52f2bec2c51cd58cb796da5643b8b4d057599df25d4e845a2d", "generation_seconds_batch": 20.924916962976567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 5.752562999725342, "genuineness": 4.457139015197754, "identity": 0.6577502489089966, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/2026d158e8f81271f97218efb55da8686b08fd99528708e9e0e18c16bb5eddaf.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "20d5b5c1546e51e96c94d89ec23740b1b226aeb87f9240b5d27a48050eb319cc", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "00461da6ad48ae7c2ae9622af7744292e5aaf910b7793d4d2d6cb1a369d18a54", "generation_seconds_batch": 25.081723792944103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04536035656929016, "target_z": -0.2285156229070101, "ce": 5.967014789581299, "genuineness": 4.607763767242432, "identity": 0.49406254291534424, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/20d5b5c1546e51e96c94d89ec23740b1b226aeb87f9240b5d27a48050eb319cc.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "215b6f691194a6f559724842dc0903356a605bed544050444fc8aef0ec479b6a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e8478838c9f830f3a69f3039577ddcf945b1b5a7167e9abfe01294860c3a246e", "generation_seconds_batch": 23.938322264002636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0019060224294662476, "target_z": -0.3066406329533616, "ce": 6.117925643920898, "genuineness": 4.507347106933594, "identity": 0.45888563990592957, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/215b6f691194a6f559724842dc0903356a605bed544050444fc8aef0ec479b6a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "21ba626d1bba0be9c0182f02351be70ad5f479b1b88a4a681c2f835e87d396c7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7766b0b08c99cc690c7c6648d628e173e67271dc4f6746e8ef6ed27753843254", "generation_seconds_batch": 17.676940452074632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007337823510169983, "target_z": -0.2968749899536485, "ce": 5.990842819213867, "genuineness": 4.419482707977295, "identity": 0.41163381934165955, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/21ba626d1bba0be9c0182f02351be70ad5f479b1b88a4a681c2f835e87d396c7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "21ca3a15896f6e8cae5f21853a9115762bc64978fbeb37fcb5efa53e71ab5a0b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "5dded7bee8656482edfab4c0de3f097841f20bf7c1543f782bb65ec7d15a0d4c", "generation_seconds_batch": 24.352556733996607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05024896562099457, "target_z": -0.21972656563948484, "ce": 5.927301406860352, "genuineness": 4.2374773025512695, "identity": 0.18377354741096497, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/21ca3a15896f6e8cae5f21853a9115762bc64978fbeb37fcb5efa53e71ab5a0b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "237a3adbc65fed517a48f63c2b93b2c9823677b9e5823b95374965ea463e7941", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "318f466a792803fc1906607f9661b952882a957770e91aff8bacb9a60cdf6397", "generation_seconds_batch": 24.903705191914923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04373082518577576, "target_z": -0.2314452997327617, "ce": 5.720792293548584, "genuineness": 4.7332844734191895, "identity": 0.7298320531845093, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/237a3adbc65fed517a48f63c2b93b2c9823677b9e5823b95374965ea463e7941.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "23a4f87b1c9eeee95e339c0a0f51fd0e6abe8a3ca2fc37f2362ca71706e14f22", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1f6062e1ca84174217e9a8da122d2a40d493d483275e54b377d8c5240a937803", "generation_seconds_batch": 22.866261070012115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 5.871703147888184, "genuineness": 4.65797233581543, "identity": 0.57320237159729, "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_Intoxication_Altered_States_of_Consciousness/23a4f87b1c9eeee95e339c0a0f51fd0e6abe8a3ca2fc37f2362ca71706e14f22.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": "23ae9280bb74c40bc41fc38784d69d886863ecfd020a825528620b1705f1d832", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2f2cb3b4510f94660b2aeabf0594a38ed5f203250c2552f93b6fcda155c26253", "generation_seconds_batch": 24.433519550948404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07903745770454407, "target_z": -0.16796875418597979, "ce": 6.0146708488464355, "genuineness": 4.720732688903809, "identity": 0.5984681844711304, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/23ae9280bb74c40bc41fc38784d69d886863ecfd020a825528620b1705f1d832.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "23efe9a16f5ed6339475dfd320a3dde7ff40b03c6b803f0a054a8c7eea690d55", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4822c918bfcdbfc8c0b9729e851d2a76c2194b7c4776c0897d7729044b8b4c21", "generation_seconds_batch": 25.652373370015994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08012381941080093, "target_z": -0.1660156229070101, "ce": 5.982900142669678, "genuineness": 4.369274139404297, "identity": 0.6978268027305603, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/23efe9a16f5ed6339475dfd320a3dde7ff40b03c6b803f0a054a8c7eea690d55.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "248f28de76dbd1cb1d11f0e6cb545666773f54e9d8d9e1cd961674c8b7d09bdb", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fd9bcf418ddd7ec6e5d43817285b7c9a7a8d4ea46ae88e545147ef760efbc332", "generation_seconds_batch": 17.897987911012024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032324060797691345, "target_z": -0.2519531178838344, "ce": 6.006728172302246, "genuineness": 4.8588056564331055, "identity": 0.6136041283607483, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/248f28de76dbd1cb1d11f0e6cb545666773f54e9d8d9e1cd961674c8b7d09bdb.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "24d24950379e4fe52a102ae93ed5733f7a88b67ee1dad87b9dc6bbba58300a6a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f8a13dd45ebeb2990d76380fad41bdb087e87b1a91b413ceccc541fd46f8063b", "generation_seconds_batch": 24.7532375799492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05731029808521271, "target_z": -0.20703124581402021, "ce": 6.062326908111572, "genuineness": 4.400654315948486, "identity": 0.6466078758239746, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/24d24950379e4fe52a102ae93ed5733f7a88b67ee1dad87b9dc6bbba58300a6a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "24e034722a9c57716ea6144d1516490010e5bdb4421c4653d7d00c5701db2e1a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "46eccea3a7a10b9573e66d2b8dbcfb6042cf124023ac4581300766a809b8516f", "generation_seconds_batch": 25.23069732589647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.012216627597808838, "target_z": -0.3320312458140202, "ce": 5.927301406860352, "genuineness": 4.934117794036865, "identity": 0.7668299674987793, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/24e034722a9c57716ea6144d1516490010e5bdb4421c4653d7d00c5701db2e1a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "24ee6e20a43247037a2889464d5497fd9e963297642e9d62a328d91405466c7c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "265e41d57fe48da89ffd687995a4af0f12051ee9a9f44faa81f2ac35acd60bdd", "generation_seconds_batch": 24.36711001896765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032324060797691345, "target_z": -0.2519531178838344, "ce": 6.419747352600098, "genuineness": 4.532451152801514, "identity": 0.27626708149909973, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/24ee6e20a43247037a2889464d5497fd9e963297642e9d62a328d91405466c7c.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "257dcea7eb30c3d81baf9527a63db37e74908d5994f30fe2f5b9fc569d895331", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1327c90a67f1f6a00fbc2a71a21c9fce69b3e26349f84c2c5d910028540e2f47", "generation_seconds_batch": 23.96797613799572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02580590546131134, "target_z": -0.2636718787673818, "ce": 6.300607204437256, "genuineness": 4.331617832183838, "identity": 0.6238440275192261, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/257dcea7eb30c3d81baf9527a63db37e74908d5994f30fe2f5b9fc569d895331.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "25838291b588399f856ea884d66286ea6128190040a6815f3bea135dd3952530", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "wording", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "702fd441913f30ef11224e2f848addc5affbf2c17169b3a40b568419747c9006", "generation_seconds_batch": 16.415425278013572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013855963945388794, "target_z": -0.2851562558603717, "ce": 5.9431867599487305, "genuineness": 4.406930446624756, "identity": 0.6968032121658325, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/25838291b588399f856ea884d66286ea6128190040a6815f3bea135dd3952530.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "2689ef8fb39c267c1b5421772888e4e1a3885b03b327e8cef1176d215da1abb9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "eeea051899cf8251ad37da4f608c805d929da5efdf4e3d3b3e8b2dea95a26229", "generation_seconds_batch": 22.74046871403698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06926023960113525, "target_z": -0.18554686872103035, "ce": 6.157639026641846, "genuineness": 4.7458367347717285, "identity": 0.6410236358642578, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/2689ef8fb39c267c1b5421772888e4e1a3885b03b327e8cef1176d215da1abb9.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "dbfec183977cf633a04ee96841f18caa36072d92c487d30a0dda096fe98495a0", "generation_seconds_batch": 15.690741015947424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.013302981853485107, "target_z": -0.3339843636978546, "ce": 6.515059471130371, "genuineness": 4.331617832183838, "identity": 0.1979006826877594, "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_Intoxication_Altered_States_of_Consciousness/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "27f850c16937eab4cb4329d1d584ea20e8ddaf25ffb7d4ae91798d2a11785486", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "wording", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7a6abc9106f90fe0f223e95ab982fffc6cd97b5abd9687ed43630d33852c04e0", "generation_seconds_batch": 17.765737155918032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03721266984939575, "target_z": -0.2431640606163091, "ce": 6.4912309646606445, "genuineness": 4.570107460021973, "identity": 0.37512677907943726, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/27f850c16937eab4cb4329d1d584ea20e8ddaf25ffb7d4ae91798d2a11785486.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "281ef8d130d0c5620f793abc3737246a3fae4749ef3443652bd32f15ef9648e2", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c0dd851cba821bead7d04da4a995c11d5d603ec49d1acde1a10e798f498fde40", "generation_seconds_batch": 25.116535856970586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1322690099477768, "target_z": -0.07226562960457775, "ce": 6.260893821716309, "genuineness": 4.432034492492676, "identity": 0.468421995639801, "hypothesis": "Ja, ik heb het kleine dootje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.1111111111111111, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/281ef8d130d0c5620f793abc3737246a3fae4749ef3443652bd32f15ef9648e2.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "285ff56a81825913e8365a3e2185ba73b8d7c6cc2422bfb91d4983f373405ec8", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "591fd9170095c1ff92ca840cdf57ade7207989bb7cb90d7b0c45a4d1642124b4", "generation_seconds_batch": 25.8399510049494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007871195673942566, "target_z": -0.3242187474884121, "ce": 5.990842819213867, "genuineness": 4.65797233581543, "identity": 0.7579134106636047, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/285ff56a81825913e8365a3e2185ba73b8d7c6cc2422bfb91d4983f373405ec8.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "288660f66385665f13d74231a1810199aa440bf5b50fab2bbe47563b836deb94", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7e1c8a0f1d3166c36ff51493f62b71180dfdb3219ef5b58e785399eaf9c64223", "generation_seconds_batch": 22.850130185019225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033410415053367615, "target_z": -0.25, "ce": 6.046441555023193, "genuineness": 4.758388519287109, "identity": 0.835758626461029, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/288660f66385665f13d74231a1810199aa440bf5b50fab2bbe47563b836deb94.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "28897e4f4af91dd285d272a5b5020afa2cfbeeb4c6effe3c5e8afad81c3e65c6", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2775b4c0bcf43b1c65d123e49d9c685f058501f8bd0972476de72dbd3c350ace", "generation_seconds_batch": 25.859083062969148, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.1894097328186035, "genuineness": 4.607763767242432, "identity": 0.477986216545105, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/28897e4f4af91dd285d272a5b5020afa2cfbeeb4c6effe3c5e8afad81c3e65c6.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "2a4c64a8dba576e8ac112da4fce19d2cbcee0cf71d84049facf225ce858bebb1", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4efa8b19eabe0fc715e1d999e0988f060642571e6dfaee8bb48d2b115e4f4158", "generation_seconds_batch": 18.72972058400046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01928776502609253, "target_z": -0.27539061286065863, "ce": 5.9431867599487305, "genuineness": 4.457139015197754, "identity": 0.6932685375213623, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/2a4c64a8dba576e8ac112da4fce19d2cbcee0cf71d84049facf225ce858bebb1.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": "2b04adcd993c2cce0d0071500db85b09d463e01bb561b482090100343797531a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "d0e78ed115b4dcaa7081861c6431498e51bd18eeeb85824670efa4b2580a4ba7", "generation_seconds_batch": 18.637672291020863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007337823510169983, "target_z": -0.2968749899536485, "ce": 6.09409761428833, "genuineness": 4.306513786315918, "identity": 0.4550309479236603, "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_Intoxication_Altered_States_of_Consciousness/2b04adcd993c2cce0d0071500db85b09d463e01bb561b482090100343797531a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "2b8a9eb7bbed55ef8113207ff7efa919a36a9cfd5e87174214b9bddf4d6dd3cd", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "87f2010e72e4941de4cfab97f63cebbd840647cb821059fae74c2b769498d7d1", "generation_seconds_batch": 23.837625812040642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 6.1020402908325195, "genuineness": 4.645420074462891, "identity": 0.7007371783256531, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/2b8a9eb7bbed55ef8113207ff7efa919a36a9cfd5e87174214b9bddf4d6dd3cd.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "2ba133cbef09f846d679f1b5c2716be6e6afc0f67b7c565a3899c0d5b8f257fd", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "287d9ce20b1286d45970e6003167bab0b8845e59fe02449f7b004661165c1cda", "generation_seconds_batch": 22.212021298939362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008424177765846252, "target_z": -0.2949218720698142, "ce": 6.022613525390625, "genuineness": 4.356721878051758, "identity": 0.7157986164093018, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/2ba133cbef09f846d679f1b5c2716be6e6afc0f67b7c565a3899c0d5b8f257fd.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "2bbbdcb94445377a5b6b29cace2ff431ec2444e654b6d6688c39e987e2464785", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2f87f6760e88f4e765777da28a584011be165e64362e4bc12e8aaa350ae1058d", "generation_seconds_batch": 23.90162192704156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0062514543533325195, "target_z": -0.2988281346277535, "ce": 6.316492557525635, "genuineness": 4.457139015197754, "identity": 0.23981831967830658, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/2bbbdcb94445377a5b6b29cace2ff431ec2444e654b6d6688c39e987e2464785.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "2bcdc5bf301517f2541386126553b7445f411214052945b67123d0161ab4fa4a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "wording", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0479c85c4295ae7968c3567a2494e8a09a4c8fdcadb8e5f9d2a1ea7a8b23de15", "generation_seconds_batch": 16.415425278013572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 6.062326908111572, "genuineness": 4.432034492492676, "identity": 0.686992883682251, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/2bcdc5bf301517f2541386126553b7445f411214052945b67123d0161ab4fa4a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "2c2539ce4c463246c413752b65e030215098158a77aba3cb72034940bb3f130e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1543789491e776f80be858d4e1e1babdc988827f2a2388e91abc8e59574e8d4f", "generation_seconds_batch": 18.521206815959886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012769609689712524, "target_z": -0.2871093737442061, "ce": 6.205295085906982, "genuineness": 4.557555198669434, "identity": 0.521979033946991, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/2c2539ce4c463246c413752b65e030215098158a77aba3cb72034940bb3f130e.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": "2c4ba5a2b5f1c7563ebcfdd6c068275794db78b8a6d83ade24eeae3f626e5e94", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3493a220d9214a27df5607431e04de66e4a337acd0514351853a7b99830ce7e6", "generation_seconds_batch": 23.355712009011768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008424177765846252, "target_z": -0.2949218720698142, "ce": 6.062326908111572, "genuineness": 4.65797233581543, "identity": 0.46244364976882935, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/2c4ba5a2b5f1c7563ebcfdd6c068275794db78b8a6d83ade24eeae3f626e5e94.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "2c7a3516fed4ce6864fbbe9c141f5e12508b11d8835a0c4a35c88e449216e9de", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "be190e5d6d8c5411dcd9b777bfbcb36645ba40c7dd987a1b0dd165e75eb223cf", "generation_seconds_batch": 19.08214870095253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08229653537273407, "target_z": -0.16210937374420606, "ce": 6.062326908111572, "genuineness": 4.356721878051758, "identity": 0.7436139583587646, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/2c7a3516fed4ce6864fbbe9c141f5e12508b11d8835a0c4a35c88e449216e9de.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "2cc3525527defb51800024cbc2968f87b44cc659c70a6e807db6d066965b2ac6", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3f2aaf1dc8c037bd5e00d9a1542341e9fe4a6ff22b0895500481e296ece2f2f5", "generation_seconds_batch": 23.76958071894478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07903745770454407, "target_z": -0.16796875418597979, "ce": 5.585766792297363, "genuineness": 4.7081804275512695, "identity": 0.4127930998802185, "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_Intoxication_Altered_States_of_Consciousness/2cc3525527defb51800024cbc2968f87b44cc659c70a6e807db6d066965b2ac6.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "2cc5dae6150efb6c0035d12d763540eee803a27ca294266fc42cd8021351aa27", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b13e995d7997500bdc017115aea511aeb9a7a79c60dcf8cec9cdee492ad8e755", "generation_seconds_batch": 24.012058028019965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05731029808521271, "target_z": -0.20703124581402021, "ce": 6.2767791748046875, "genuineness": 4.6705241203308105, "identity": 0.6329076290130615, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/2cc5dae6150efb6c0035d12d763540eee803a27ca294266fc42cd8021351aa27.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "2ce20bc700cff0d4d2325a45e9b3072d62f718bcb0136ec87c049721ee1d92e7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "387a4f53770f3828123d9ea053cefc6efc38de0a5e91517abdb81431f366ca32", "generation_seconds_batch": 24.293421749025583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011130273342132568, "target_z": -0.3300781279301858, "ce": 6.149696350097656, "genuineness": 4.6956281661987305, "identity": 0.5851740837097168, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/2ce20bc700cff0d4d2325a45e9b3072d62f718bcb0136ec87c049721ee1d92e7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "2d10d6cb90f28454bcb1be5659a873944821baad54097af259be54ff36a19b41", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "cfdcfc8de96e857a932bc6815edd113a385b55b043d6a31154c6a696b4caee4a", "generation_seconds_batch": 18.258221653057262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030151337385177612, "target_z": -0.2558593804417737, "ce": 6.24500846862793, "genuineness": 4.6705241203308105, "identity": 0.5024247169494629, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/2d10d6cb90f28454bcb1be5659a873944821baad54097af259be54ff36a19b41.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "2d4644dc5294f1f69a6ca85031143705e133be44d3bf333f6ba8650406b6cdd5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0f5984f461c05435cacd81e449f73fd5c1ca70bfa9cc46adfbc7581b59a95a76", "generation_seconds_batch": 19.718848824035376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014942318201065063, "target_z": -0.2832031379765373, "ce": 6.181467056274414, "genuineness": 4.582659721374512, "identity": 0.8205198645591736, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/2d4644dc5294f1f69a6ca85031143705e133be44d3bf333f6ba8650406b6cdd5.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "2d5910b3ad3cbf15f9526741bee6cfdf004f0f48c3fdeaa269bed8c18f95d386", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "cd712dfdd3fcc7f9bf55d8c72cd92ab8d433c1e808774cf452e17bf3c13d135b", "generation_seconds_batch": 24.233384798048064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003525763750076294, "target_z": -0.316406249162804, "ce": 6.022613525390625, "genuineness": 4.720732688903809, "identity": 0.7443355321884155, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/2d5910b3ad3cbf15f9526741bee6cfdf004f0f48c3fdeaa269bed8c18f95d386.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "2d64810bdc739032e95020f4786cc141fa2b9030ba302f94838fe40954b0de7c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d566d0f2ab7cffa01a9e71f8d224ad3135fee31d972d9efdf291f46fad09c945", "generation_seconds_batch": 22.949570272001438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.165581703186035, "genuineness": 4.846253395080566, "identity": 0.7538235783576965, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/2d64810bdc739032e95020f4786cc141fa2b9030ba302f94838fe40954b0de7c.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "2de8ed88a81ee6eed73ba0793d0ba80d2362cf53a8eabac62c1e254c36f5c43e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3053bf36a14738d5fe05307af456d35ad9ed27da4e40e45390d83aa1a2871687", "generation_seconds_batch": 28.66196233103983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.052964866161346436, "target_z": -0.2148437441396283, "ce": 6.268836498260498, "genuineness": 4.6203155517578125, "identity": 0.6583134531974792, "hypothesis": "De deur staat nog open. Ik heb je jas op je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.15789473684210525, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/2de8ed88a81ee6eed73ba0793d0ba80d2362cf53a8eabac62c1e254c36f5c43e.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": "2e8660e82c5682d6e84ba18e876e1a0294bd33542566774ac3a799700977dfc7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f714e4bd8a7f6dec48238a24cb1b1659c1190d8245df509769170703a64f4d05", "generation_seconds_batch": 24.9421005230397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10076462477445602, "target_z": -0.12890624916280405, "ce": 5.704906940460205, "genuineness": 4.432034492492676, "identity": 0.6233351230621338, "hypothesis": "Escribí el número en el sobre. Léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/2e8660e82c5682d6e84ba18e876e1a0294bd33542566774ac3a799700977dfc7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "2f630f3c9aa1e933cff1146ac5189e76ed741601b19a98a584eecec1ca1c5377", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2457bee131c58c19287b848eaa0ab64cd2d33627f5d151d2273f57b2b7316bff", "generation_seconds_batch": 24.23090731690172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02146047353744507, "target_z": -0.2714843770929899, "ce": 6.181467056274414, "genuineness": 4.632867813110352, "identity": 0.6838829517364502, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/2f630f3c9aa1e933cff1146ac5189e76ed741601b19a98a584eecec1ca1c5377.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "2f9936ab434a9ad2eca2be62c5507c34d868d4f2816a532bdbc2fa5f46833a02", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8f68aeb7fb6fc438c86c4fcbd96c0955be72677b8a17ee50bb6ff2958c524939", "generation_seconds_batch": 24.429336349014193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02146047353744507, "target_z": -0.2714843770929899, "ce": 6.006728172302246, "genuineness": 4.532451152801514, "identity": 0.6853287220001221, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/2f9936ab434a9ad2eca2be62c5507c34d868d4f2816a532bdbc2fa5f46833a02.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": "30738a826a1fc613b9da25dd2f69d693823edfabd08cd895c1d604ae1ad5900a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "45abeb4a35447d696b2ced88b2f38dac0315cbf51dbb16e0e5da14e5a38556b6", "generation_seconds_batch": 19.252458452945575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02580590546131134, "target_z": -0.2636718787673818, "ce": 5.77639102935791, "genuineness": 4.6956281661987305, "identity": 0.8245437145233154, "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_Intoxication_Altered_States_of_Consciousness/30738a826a1fc613b9da25dd2f69d693823edfabd08cd895c1d604ae1ad5900a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "308d3b8968da1bd6ed511e06ab681f5f6eb3a5fbe47dd7ef64bcc668590e0edd", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "39350fb5d9c5d4bffc7738cd55d113dddc3163ac4e70a4b1ce58540c55192559", "generation_seconds_batch": 24.174554062075913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08229653537273407, "target_z": -0.16210937374420606, "ce": 6.149696350097656, "genuineness": 4.507347106933594, "identity": 0.2871449887752533, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/308d3b8968da1bd6ed511e06ab681f5f6eb3a5fbe47dd7ef64bcc668590e0edd.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": "30a50411a59384e8b0d442644ee70c6ae87d51abc0718483f7b8b2cbe503938b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5000f95a6a713f15c6eda92a96d8614492b7c3493844d7a87f2a49cdca7f8f1d", "generation_seconds_batch": 22.719784097978845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003525763750076294, "target_z": -0.316406249162804, "ce": 6.1894097328186035, "genuineness": 4.519899368286133, "identity": 0.6474488973617554, "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_Intoxication_Altered_States_of_Consciousness/30a50411a59384e8b0d442644ee70c6ae87d51abc0718483f7b8b2cbe503938b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "315de63e8bb55c1440f737ed0ea96ac7313d090c4e4217131a76265b74b839fc", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3a326d19fc471b12563ea64a6432dbe6d8bb8a7aa43a50354bb85d3a53410c62", "generation_seconds_batch": 26.64299234491773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.005698487162590027, "target_z": -0.3203125117207434, "ce": 6.086154937744141, "genuineness": 4.6203155517578125, "identity": 0.649262011051178, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/315de63e8bb55c1440f737ed0ea96ac7313d090c4e4217131a76265b74b839fc.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "3169f136eb1e5a920c3cfec5fc9316eb760777e41147a02ed63c96baab78f56d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "739acb9e1c9d176792a37762983ccaab2cc5641067fb857f60c2808f52f6db2d", "generation_seconds_batch": 23.958118160022423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.046989887952804565, "target_z": -0.22558594608125854, "ce": 6.1894097328186035, "genuineness": 4.532451152801514, "identity": 0.5267447233200073, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/3169f136eb1e5a920c3cfec5fc9316eb760777e41147a02ed63c96baab78f56d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "316c3f82a3f3a344a9f3743990f5bc1ebc24e8d9b484c7be8ca85eea9e30abc7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "88f816a4507a54fe8a6f94010e55ab4e3aac3de1233f54c42b06dbfe13ece279", "generation_seconds_batch": 17.84913006098941, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.001353040337562561, "target_z": -0.3124999866048647, "ce": 6.1894097328186035, "genuineness": 4.65797233581543, "identity": 0.3903167247772217, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/316c3f82a3f3a344a9f3743990f5bc1ebc24e8d9b484c7be8ca85eea9e30abc7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "31c43cf972db0a7e36a27b3533026780eef9101216fc06274aff957bfdfff64f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "df10d59bbe4368e363f8d13de1f5dc76526a1ed18f510ea294cee97dd9eaec65", "generation_seconds_batch": 18.82229852594901, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03938537836074829, "target_z": -0.23925782484864033, "ce": 6.213237762451172, "genuineness": 4.432034492492676, "identity": 0.2277417778968811, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/31c43cf972db0a7e36a27b3533026780eef9101216fc06274aff957bfdfff64f.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "31f4e0dfa96a50a62db883456aa7005f8bc664ecf3d544a77ef6a880cb7a6f36", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "3faae334c68863a795a11d145e990e85ae3bbf61920b75cc5a255f3398d58c18", "generation_seconds_batch": 18.945048050954938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05350804328918457, "target_z": -0.2138671851977111, "ce": 5.708878040313721, "genuineness": 4.570107460021973, "identity": 0.5918092131614685, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/31f4e0dfa96a50a62db883456aa7005f8bc664ecf3d544a77ef6a880cb7a6f36.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "3204807e80bd6387e400cd1fa82259a7286dfe0a399d1d7c6d50f104b14ec48b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "38c39d4666d523c3bfe896843ef0c1c9eafedbc815f45b900d7997f858e6cac1", "generation_seconds_batch": 23.834383687004447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.000819668173789978, "target_z": -0.308593750837196, "ce": 6.078212261199951, "genuineness": 4.243753433227539, "identity": 0.6528939008712769, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/3204807e80bd6387e400cd1fa82259a7286dfe0a399d1d7c6d50f104b14ec48b.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": "32093ab35ecad91b0c5dd178560e97d0df9902a95c2be3aa536a17ade9e260e9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "a73b300c106730f532416a6713a34edd5bce397013dcbd352826ec90d3bb2557", "generation_seconds_batch": 17.11550425796304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.181467056274414, "genuineness": 4.65797233581543, "identity": 0.442080020904541, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, lies sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/32093ab35ecad91b0c5dd178560e97d0df9902a95c2be3aa536a17ade9e260e9.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "3212fab7fe42d6bb0a8f89353729d2df747dbc3e7b058352ad27a84ada97b405", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0fd01ba55b260708e0af2d2a1348bb101a24e44e8a85fb392db1121d3eb666ab", "generation_seconds_batch": 23.117969604907557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031237691640853882, "target_z": -0.2539062625579393, "ce": 6.24500846862793, "genuineness": 4.306513786315918, "identity": 0.60648113489151, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/3212fab7fe42d6bb0a8f89353729d2df747dbc3e7b058352ad27a84ada97b405.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "323956f85c0e3b9902785c109d7b11483830df2ee4169f6086d50898e2d52836", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b700a125213b3c62f4df75bf0e2228f33674f4789b96b4ae27a03ca73bde1d84", "generation_seconds_batch": 25.811902847955935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02146047353744507, "target_z": -0.2714843770929899, "ce": 6.197352409362793, "genuineness": 4.570107460021973, "identity": 0.3498796820640564, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/323956f85c0e3b9902785c109d7b11483830df2ee4169f6086d50898e2d52836.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "3358b032e0e89e86e2cbad5682748fda10879f8c997cf83174123ca8fca0b0cf", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1d991849e3f157da1d3b5aea76c49ad76d75ef7488ef5288c5878469adb6e1ca", "generation_seconds_batch": 17.209769928944297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011683255434036255, "target_z": -0.28906249162804043, "ce": 5.903473377227783, "genuineness": 4.821148872375488, "identity": 0.6531391143798828, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/3358b032e0e89e86e2cbad5682748fda10879f8c997cf83174123ca8fca0b0cf.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "3369c08f7092338a0d5fde2ccf39d5a12ad358308994f939a7d79217ab69b9c8", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c9ddede45ea9269b0a3adc7a375370752094c7c6a9c0b0ae8c0c681bd6354bb5", "generation_seconds_batch": 23.854810334043577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030151337385177612, "target_z": -0.2558593804417737, "ce": 6.1020402908325195, "genuineness": 4.331617832183838, "identity": 0.8072785139083862, "hypothesis": "De deur staat nog open. Ik heb voelt je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/3369c08f7092338a0d5fde2ccf39d5a12ad358308994f939a7d79217ab69b9c8.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": "338401f5cbf605c4f6505703836401df7b8d4e0672075d0f006c799f164fd9a5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0cc872311ac528aaf7b2814800d3b27ae9c7ad8663b3f989c86d9a4fd817e2e3", "generation_seconds_batch": 18.416026331018656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031237691640853882, "target_z": -0.2539062625579393, "ce": 5.903473377227783, "genuineness": 4.821148872375488, "identity": 0.6497287750244141, "hypothesis": "Bien, he movido la pequeña silla azul. 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_Intoxication_Altered_States_of_Consciousness/338401f5cbf605c4f6505703836401df7b8d4e0672075d0f006c799f164fd9a5.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "09349afcc065d1c908026c9325aa9534542d05bfb78a6147a875ea4c81cb19f2", "generation_seconds_batch": 16.68161378300283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01438935101032257, "target_z": -0.33593750837195957, "ce": 6.173524379730225, "genuineness": 4.457139015197754, "identity": 0.706951379776001, "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_Intoxication_Altered_States_of_Consciousness/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "34747afb3aa60b00a708a35e37cd37d9f0c63df11753d47b47266aed20dbcebd", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "08653fe5fdd4b84f45278a2ff66cccdfbf39ad79caaa10327bfcce38d1c66d60", "generation_seconds_batch": 23.0252912879223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.038842201232910156, "target_z": -0.24023438379055753, "ce": 5.974957466125488, "genuineness": 4.557555198669434, "identity": 0.13496851921081543, "hypothesis": "Ik heb het een klein doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/34747afb3aa60b00a708a35e37cd37d9f0c63df11753d47b47266aed20dbcebd.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "1065b44c15b363fa0523b8288fc8564105fc93c436c39b4bfd5da6b81b397965", "generation_seconds_batch": 16.92203227209393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007337823510169983, "target_z": -0.2968749899536485, "ce": 6.483288764953613, "genuineness": 4.093128204345703, "identity": 0.26923543214797974, "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_Intoxication_Altered_States_of_Consciousness/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "34a51708604c04f9df1f306a338dda59490e08f4ace6fd0253bc7dba123a6c91", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "29a209db68768341e6c32e3a5b706af9a3915de211df67c6fb65740f6c879323", "generation_seconds_batch": 17.92101502593141, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06600116193294525, "target_z": -0.19140624916280405, "ce": 6.006728172302246, "genuineness": 4.262581825256348, "identity": 0.24171900749206543, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/34a51708604c04f9df1f306a338dda59490e08f4ace6fd0253bc7dba123a6c91.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": "34c35ecda577081a4fcd4618c5379fc9a0dd544e008d3bc382ad74428780b98e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "572d61ab9be06efb8d79a0d176bc9b79a56873ba6adedeff4b73db582ece911b", "generation_seconds_batch": 24.193830174044706, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.045903533697128296, "target_z": -0.2275390639650929, "ce": 6.41180419921875, "genuineness": 4.557555198669434, "identity": 0.20157018303871155, "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_Intoxication_Altered_States_of_Consciousness/34c35ecda577081a4fcd4618c5379fc9a0dd544e008d3bc382ad74428780b98e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "34c7a36433208a830f80c16ce81af622c3824008d7a2ac6f8a744d2d2da95e8e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "43a41f7876b71d460ba7306350f5515f1131c8491e6f56f79c8c18b697c61122", "generation_seconds_batch": 17.676940452074632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06274208426475525, "target_z": -0.19726562960457775, "ce": 6.1894097328186035, "genuineness": 4.381826400756836, "identity": 0.4408196210861206, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/34c7a36433208a830f80c16ce81af622c3824008d7a2ac6f8a744d2d2da95e8e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "355150d9fcfa19a8e4192399b9fadf436d14978fafd17faf7f3368e0e1b2f870", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d497fc915bd78de277416aaa7ff9289a79e2adacc6de7f8bcee2546d00d34f0b", "generation_seconds_batch": 25.20246985205449, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01656205952167511, "target_z": -0.3398437441396283, "ce": 6.086154937744141, "genuineness": 4.413206577301025, "identity": 0.6836807727813721, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/355150d9fcfa19a8e4192399b9fadf436d14978fafd17faf7f3368e0e1b2f870.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "355f88ea8355aca6e77e0c984bb992ca9b6dde7332d6b1674f9ec939fe057ac8", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8e4813bcca9401edfdfd42ee43655ae8c5eb43a2b3cef3b39692aed9ed4bb6f6", "generation_seconds_batch": 25.20246985205449, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26915013790130615, "target_z": 0.17382810783748293, "ce": 6.205295085906982, "genuineness": 4.494794845581055, "identity": 0.24725061655044556, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen daar samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/355f88ea8355aca6e77e0c984bb992ca9b6dde7332d6b1674f9ec939fe057ac8.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "35894cd48f3b1576a36ee89b5b43bf1b214a9f2ad55af31bf7e044d7f0aa9e22", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8cd6ec57cfed1dbc33c6ee2851e81f966eacb45c5b3dc9ad26cc69d263631c2b", "generation_seconds_batch": 24.27008806192316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13770079612731934, "target_z": -0.06250001339513528, "ce": 6.165581703186035, "genuineness": 4.65797233581543, "identity": 0.24575841426849365, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/35894cd48f3b1576a36ee89b5b43bf1b214a9f2ad55af31bf7e044d7f0aa9e22.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "35aba3b235244c3a03207eca1ca356e729037d706ec919f3e14545e6cc5db5bb", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cc661992c2cf896cc5054c75f01befdb9c17b4cdc43d68701c423708528f175d", "generation_seconds_batch": 21.85392303694971, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.005698487162590027, "target_z": -0.3203125117207434, "ce": 5.959072113037109, "genuineness": 4.7081804275512695, "identity": 0.6986661553382874, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/35aba3b235244c3a03207eca1ca356e729037d706ec919f3e14545e6cc5db5bb.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "36376a17730ac4dc187a46a3a6e975250c5b7b3545481a866e009637f5581d0a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "13cb6e8919477dfb526b84c73da8b9c9f47ffff2cb8996fb27696bf614eabbf5", "generation_seconds_batch": 22.467835608054884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02146047353744507, "target_z": -0.2714843770929899, "ce": 6.348263263702393, "genuineness": 4.770940780639648, "identity": 0.6948236227035522, "hypothesis": "La porte, encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/36376a17730ac4dc187a46a3a6e975250c5b7b3545481a866e009637f5581d0a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "36a3394c9c714ae330fe8da5a71575daf891e6b051e027de2441c52b7c10de58", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "8f7e41bedd232771e84ac7cb16615058dd672450f5d7aa1e596dd32dd48b1edc", "generation_seconds_batch": 17.90225799102336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25611385703086853, "target_z": 0.1503906396509292, "ce": 6.149696350097656, "genuineness": 4.482243061065674, "identity": 0.7695500254631042, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/36a3394c9c714ae330fe8da5a71575daf891e6b051e027de2441c52b7c10de58.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": "36d6eb51305c23c428698223495cfe7e70870f63d1283bc04454a975577ab176", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "968f23a0388d6a05acefdcb5ecc5958272aacbd8aa90012947646a5fea9fee34", "generation_seconds_batch": 23.374196961987764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 6.284721851348877, "genuineness": 4.645420074462891, "identity": 0.589148759841919, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/36d6eb51305c23c428698223495cfe7e70870f63d1283bc04454a975577ab176.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": "36f5929c0b70782aa605381dd3955c97c1428f8d839019764bf3ca570b87a5dd", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "194dee16164774a1f58d95cdbe57bcf815e04a23f857a2e0a5f76a8878077e9e", "generation_seconds_batch": 17.66118654201273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 5.784333229064941, "genuineness": 4.65797233581543, "identity": 0.6735004186630249, "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_Intoxication_Altered_States_of_Consciousness/36f5929c0b70782aa605381dd3955c97c1428f8d839019764bf3ca570b87a5dd.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "373c1518dcf2690e67f50d53d880ea98f2ea7a2d2ed8814d61ccbecac97f6715", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2929ebad7ed66a4347021189a559fe8b830bb5b32dd355d0ebc8dbb4fcc9e6ea", "generation_seconds_batch": 17.756876370985992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03721266984939575, "target_z": -0.2431640606163091, "ce": 6.332377910614014, "genuineness": 4.15588903427124, "identity": 0.5462414622306824, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/373c1518dcf2690e67f50d53d880ea98f2ea7a2d2ed8814d61ccbecac97f6715.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "3756979ae714e4cbacb84f819e5d048ad3a708c67dca5c918e11cab121d43917", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "wording", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "58c7b10e11b18a05a3720dfad1ecf1249d49f3f83e72a071ad0c9f6763633b98", "generation_seconds_batch": 16.696726626018062, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008424177765846252, "target_z": -0.2949218720698142, "ce": 6.157639026641846, "genuineness": 4.394378662109375, "identity": 0.5513513684272766, "hypothesis": "Ja, ik heb het kleine 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_Intoxication_Altered_States_of_Consciousness/3756979ae714e4cbacb84f819e5d048ad3a708c67dca5c918e11cab121d43917.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "377737e10ebd9889a8a8dd17f40712accdd162d9f0c95f519234f5412ada21cc", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "58ce13d153d6eb26b1d7631719f1845bd74c81e16dd43ac30c26e06db2bcf09d", "generation_seconds_batch": 24.39488734700717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06056936830282211, "target_z": -0.2011718787673818, "ce": 5.7128496170043945, "genuineness": 4.770940780639648, "identity": 0.6982927322387695, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/377737e10ebd9889a8a8dd17f40712accdd162d9f0c95f519234f5412ada21cc.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "379ac43e50d664a6d72d6ce0195bba1f4a421354308924e0d76f56aa68d46f75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "99e4f2eaa44e5d73114d4a85ba117d9b51d4487008729dd8bbd4109c08516928", "generation_seconds_batch": 22.91860142594669, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.173524379730225, "genuineness": 4.68307638168335, "identity": 0.7144573926925659, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/379ac43e50d664a6d72d6ce0195bba1f4a421354308924e0d76f56aa68d46f75.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "379c7672ed1ca77ffbb9fe9a0f0ac838c8b20ffebd0ddf7cfeada67587c295ac", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1adff8164dfca98593f67ca9d5a242c9fab57408b12c5c2116d6fc23f5966b30", "generation_seconds_batch": 18.00209329405334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06328526884317398, "target_z": -0.1962890572675253, "ce": 6.165581703186035, "genuineness": 4.582659721374512, "identity": 0.5511709451675415, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/379c7672ed1ca77ffbb9fe9a0f0ac838c8b20ffebd0ddf7cfeada67587c295ac.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "37cd99c57abccae4f83d4ac6e3e26366ef3562e8d3327a90d9a137ff6c8bde2e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "73b791d122ae7b2fbefde8e2c33f3fb3f14510655c3652a5f7c3a042c4d469d0", "generation_seconds_batch": 27.629419628996402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 6.078212261199951, "genuineness": 4.65797233581543, "identity": 0.8631372451782227, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/37cd99c57abccae4f83d4ac6e3e26366ef3562e8d3327a90d9a137ff6c8bde2e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "384803a5bbb37a19ce8320b295c3607e1f09e50d88ccd391b975cb580faa359f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "fb260cd8c70f3cd6f399bb11f8678b6307fc7b557f814caec7e3bb9e2cf1aff3", "generation_seconds_batch": 25.419156046933495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1148872822523117, "target_z": -0.10351562290701011, "ce": 5.927301406860352, "genuineness": 4.331617832183838, "identity": 0.7462912797927856, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/384803a5bbb37a19ce8320b295c3607e1f09e50d88ccd391b975cb580faa359f.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "38503390da63dbe1d3cccc3e90d0186d21397c417da60d4208da9fb14b59893a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8dd0a2dc0f8db53408a9cbec77c72e66798b9b61255998581cf66a7f0e445ba5", "generation_seconds_batch": 27.260813537985086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010596886277198792, "target_z": -0.2910156363021454, "ce": 6.149696350097656, "genuineness": 4.770940780639648, "identity": 0.5759907364845276, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/38503390da63dbe1d3cccc3e90d0186d21397c417da60d4208da9fb14b59893a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "386b27fb173d7398845ec433f97c47a13a14564ed6b37468676ff3417b6b0c11", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d399ee9d67cf4e27ed1092ccfa0b0cfce12a47a326a709f173ca51ac7b4124b6", "generation_seconds_batch": 25.322038265992887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.000819668173789978, "target_z": -0.308593750837196, "ce": 5.998785495758057, "genuineness": 4.758388519287109, "identity": 0.7563902139663696, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/386b27fb173d7398845ec433f97c47a13a14564ed6b37468676ff3417b6b0c11.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "392bb57c06d18b9a23910a876a085aa16009346f0133942f9fbdc8799af847c3", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b3c82abdf11a08e765d6122d01102c1565feadb97c14b1d6c5547a89d6cb8361", "generation_seconds_batch": 23.279175449046306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0507921427488327, "target_z": -0.21875000669756764, "ce": 5.728734970092773, "genuineness": 4.632867813110352, "identity": 0.7092273235321045, "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_Intoxication_Altered_States_of_Consciousness/392bb57c06d18b9a23910a876a085aa16009346f0133942f9fbdc8799af847c3.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "394ad9383057c5ed9ec2ceb7554113f7464a0c10abe2e7fe2780482e0614ad2d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "19def8142cd779e073bb925780ee0491fd61378ceb56357eb551b0a1978b298f", "generation_seconds_batch": 18.271980960969813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02146047353744507, "target_z": -0.2714843770929899, "ce": 6.348263263702393, "genuineness": 4.256305694580078, "identity": 0.20176485180854797, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/394ad9383057c5ed9ec2ceb7554113f7464a0c10abe2e7fe2780482e0614ad2d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "394cfdcf2d9adf0399cddd3dfbbdc2585fd023782ed6d722ac8a89c48970de04", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "59008dcbe461aaa7af68c396fd8704e5194937ca0cfc50dc1c7f01946283fc99", "generation_seconds_batch": 23.736711986013688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.034496769309043884, "target_z": -0.2480468821161656, "ce": 6.054384231567383, "genuineness": 4.7332844734191895, "identity": 0.750635027885437, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/394cfdcf2d9adf0399cddd3dfbbdc2585fd023782ed6d722ac8a89c48970de04.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": "39ca72a3a67346a118c473e3c50dfcce98e81fcb22a85aa05b231e200e48380f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5948edd3c04a2739d3ce5dff2d017d02b0c07490a1d840a762e6d9018b11a0f3", "generation_seconds_batch": 22.58985648700036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05731029808521271, "target_z": -0.20703124581402021, "ce": 5.919358730316162, "genuineness": 4.65797233581543, "identity": 0.6876591444015503, "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_Intoxication_Altered_States_of_Consciousness/39ca72a3a67346a118c473e3c50dfcce98e81fcb22a85aa05b231e200e48380f.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "3a1d6383ca9d0d6fb33ff270ec0e33ba6d5d218a1c93cd4a883f534fca90d2c3", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "fd80e2bded364aab77ace23a1ff0dd09e2e7d072a65245e9df6f7ae0f374eb54", "generation_seconds_batch": 17.17176111205481, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05731029808521271, "target_z": -0.20703124581402021, "ce": 6.205295085906982, "genuineness": 4.582659721374512, "identity": 0.6925725936889648, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/3a1d6383ca9d0d6fb33ff270ec0e33ba6d5d218a1c93cd4a883f534fca90d2c3.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "3a82e3f29ad7393cffe821bcf48c783505a5551794970b0c0e26d65db85ec234", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "68ca1b7b6f20ab2757587c21efe3096093d9c29cffbb8c18f6a6392e0c42a6ce", "generation_seconds_batch": 24.39488734700717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 5.49045467376709, "genuineness": 4.6203155517578125, "identity": 0.5911005735397339, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/3a82e3f29ad7393cffe821bcf48c783505a5551794970b0c0e26d65db85ec234.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "3abc7113eb060fa017e507c42aae7466e57ee5f54e502c0e1a42ae87beaa8635", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "983b94289b6011d0974b185a98df84bcc42d0b9edf148f7787f7f7595911e986", "generation_seconds_batch": 25.32544534804765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.021993860602378845, "target_z": -0.34960938713934137, "ce": 6.141753673553467, "genuineness": 4.419482707977295, "identity": 0.6375921964645386, "hypothesis": "Ik heb de kleine 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_Intoxication_Altered_States_of_Consciousness/3abc7113eb060fa017e507c42aae7466e57ee5f54e502c0e1a42ae87beaa8635.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "3b055f0cc34f231c675cef7ef3b33343fd47ffca17e94706df50ae3b9cac0083", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "42afbaf1f6c86ab592951818edcdf87c6e95503ba435588b75b3fbfe4b5a25a0", "generation_seconds_batch": 22.738505361950956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031237691640853882, "target_z": -0.2539062625579393, "ce": 6.197352409362793, "genuineness": 4.369274139404297, "identity": 0.6084100008010864, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/3b055f0cc34f231c675cef7ef3b33343fd47ffca17e94706df50ae3b9cac0083.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "3b21cffebe82358a16a1899e25105c7f2f7606803092b49b246bdf34df7aacca", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "75ae60a4069e8f5a6fd7c453c7e0ea8043ac5795aeb90e49d726ce2c705dfe52", "generation_seconds_batch": 23.912631349056028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06056936830282211, "target_z": -0.2011718787673818, "ce": 5.871703147888184, "genuineness": 4.494794845581055, "identity": 0.5162457227706909, "hypothesis": "Die die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/3b21cffebe82358a16a1899e25105c7f2f7606803092b49b246bdf34df7aacca.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "3b65d21e43178b24927a5b776de2e95c6b70ce291cda4400e678de78a116a9ea", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "84a355ee13ff69a1deee82f96e3cc474343dc095025a5c4abe754f5e67d98b69", "generation_seconds_batch": 24.2948253309587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.292664527893066, "genuineness": 4.394378662109375, "identity": 0.30243581533432007, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/3b65d21e43178b24927a5b776de2e95c6b70ce291cda4400e678de78a116a9ea.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "3b756c2a8cae421642ff92cabe20d96da4bd9b0ebafe0c0e8478843a96e4f2bc", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9b01254ea074fd889451bb1f7578ddfddaf1e0ed572afec2cb30655a2d72e2c4", "generation_seconds_batch": 26.214998690993525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06926023960113525, "target_z": -0.18554686872103035, "ce": 5.919358730316162, "genuineness": 4.3504462242126465, "identity": 0.6454336643218994, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/3b756c2a8cae421642ff92cabe20d96da4bd9b0ebafe0c0e8478843a96e4f2bc.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "7121d2b1006c0077f03824c262afad741904a7d252c7764c656439ed99a230f9", "generation_seconds_batch": 17.64834172395058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 5.982900142669678, "genuineness": 4.362998008728027, "identity": 0.7159457206726074, "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_Intoxication_Altered_States_of_Consciousness/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "3cea3a4d46f9841ce5b15e2ffb1d08e14d460d79adca76966d4c6aadf24be916", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f92d38fe4a3d78eb3c4777933276710b0c54198ab9e6cbf131661f027034de8c", "generation_seconds_batch": 26.977900256984867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04536035656929016, "target_z": -0.2285156229070101, "ce": 6.300607204437256, "genuineness": 4.482243061065674, "identity": 0.41404271125793457, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/3cea3a4d46f9841ce5b15e2ffb1d08e14d460d79adca76966d4c6aadf24be916.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "3cf51177fb295fe08d4e63125491cd590c45301a6823600b98234c79b2d6600a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a357059904f8a617bac6635c0a5dd173d77e0227a9f0398fc8fd1e893c034f40", "generation_seconds_batch": 23.928583185072057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016028687357902527, "target_z": -0.2812499933024324, "ce": 5.6413655281066895, "genuineness": 4.808597087860107, "identity": 0.5902913808822632, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/3cf51177fb295fe08d4e63125491cd590c45301a6823600b98234c79b2d6600a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "3d2d0b67bac9e9e540b6d88a9350c3d8ccd11967304ead5dccb49123ccc1a09a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0dbe80115a23646dc31f005e0c1c17888c28946506c9ab88491cd90a3f117f7c", "generation_seconds_batch": 16.690037024090998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04210127890110016, "target_z": -0.2343750033487838, "ce": 6.109982967376709, "genuineness": 4.419482707977295, "identity": 0.4501814842224121, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/3d2d0b67bac9e9e540b6d88a9350c3d8ccd11967304ead5dccb49123ccc1a09a.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": "3d8ce06dd16d22be9ffd25b15b81f93243f3d9ff568348968d7f63732f364720", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78976edb4f6ad2f2ff4f841fb8b63718ccbff949b1b9048e20640e42d855c658", "generation_seconds_batch": 18.830068978946656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012769609689712524, "target_z": -0.2871093737442061, "ce": 6.070269584655762, "genuineness": 4.444586753845215, "identity": 0.5344262719154358, "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_Intoxication_Altered_States_of_Consciousness/3d8ce06dd16d22be9ffd25b15b81f93243f3d9ff568348968d7f63732f364720.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "3d962d340e74cffb392593a12bcc315cec2798b19b48dc5b002e9892472a1685", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9293965b21caf4d27039bda69865f0221628ae86de21c0cdc6e6dab9fe6a91c0", "generation_seconds_batch": 22.725624848040752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 6.403861999511719, "genuineness": 4.632867813110352, "identity": 0.4406576454639435, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/3d962d340e74cffb392593a12bcc315cec2798b19b48dc5b002e9892472a1685.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "3e2f8519f93b02963a9a4a50adb817af095e1abf1177c76fc601319ec5971b8b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "39e02ae80bf7cd84f630228a41e1eb5232d70ac0f69f078345395b30e735b369", "generation_seconds_batch": 24.726610089070164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03666949272155762, "target_z": -0.2441406195582263, "ce": 6.078212261199951, "genuineness": 4.532451152801514, "identity": 0.4524737596511841, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/3e2f8519f93b02963a9a4a50adb817af095e1abf1177c76fc601319ec5971b8b.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": "3ec69ec576285e4ca29da8efc0a2f238eb648d8eb6b78d0445d242dce7160206", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6fa5a607ee03572597f80ba283b74d8395d06a393ad6787239aab017eb8998f7", "generation_seconds_batch": 18.830068978946656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016028687357902527, "target_z": -0.2812499933024324, "ce": 6.0146708488464355, "genuineness": 4.582659721374512, "identity": 0.3838863968849182, "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_Intoxication_Altered_States_of_Consciousness/3ec69ec576285e4ca29da8efc0a2f238eb648d8eb6b78d0445d242dce7160206.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "3fb5789718a6317b8390bc0b99abd905dfaf4e6da8f51d2e3beeae8dd0591913", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "dc5bbf88e94fb9ca8139cc8ef830001716b4d9021fd0e871f2f91b326fe98dec", "generation_seconds_batch": 22.738505361950956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04427400231361389, "target_z": -0.2304687407908445, "ce": 6.435632705688477, "genuineness": 4.595211505889893, "identity": 0.6075518131256104, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/3fb5789718a6317b8390bc0b99abd905dfaf4e6da8f51d2e3beeae8dd0591913.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": "3ff6a9e8cdeef21b6ec8b9f9cb6deb94a2d4c0b26ef83aa180d9f96b8c744fbb", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "87579799a7c10ff604ab9355af0eb514ec2a3dcea7ae27757b3ba3f7130f727e", "generation_seconds_batch": 24.193830174044706, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.045903533697128296, "target_z": -0.2275390639650929, "ce": 6.475345611572266, "genuineness": 4.557555198669434, "identity": 0.47563502192497253, "hypothesis": "Uh the road turns left behind the bridge. Keep going until you reach this small wooden gate. I I will meet you on the other side.", "wer": 0.125, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/3ff6a9e8cdeef21b6ec8b9f9cb6deb94a2d4c0b26ef83aa180d9f96b8c744fbb.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "4126a0a011fbba6706334b2941d929990750fd778ec8370790973cb96f67bee9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "822cac83d027c143d587b8fbc9cd119bab92dc12bb5d2b9ba1d63ba2b6fab535", "generation_seconds_batch": 18.97511276905425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011683255434036255, "target_z": -0.28906249162804043, "ce": 6.022613525390625, "genuineness": 4.432034492492676, "identity": 0.6098006367683411, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/4126a0a011fbba6706334b2941d929990750fd778ec8370790973cb96f67bee9.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "429d630a87bab8e956c286cc459c527bde5d7a74eafe50b9448c546586386dd9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ec74548c0cfdbc00d69bac2937f4ce2dfccdc6d072ff65f8dc784350e0a3b19a", "generation_seconds_batch": 24.98406537505798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01928776502609253, "target_z": -0.27539061286065863, "ce": 5.927301406860352, "genuineness": 4.21237325668335, "identity": 0.5153242945671082, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/429d630a87bab8e956c286cc459c527bde5d7a74eafe50b9448c546586386dd9.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": "42ea515c27700bee66733c5285adb5d052e3effc9614de89b8d24fdd5ee5b641", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "61ce25b85d1f63546cf3657df3222f6ea9455dc10466c1d33a03a102adcf2f38", "generation_seconds_batch": 15.9018787589157, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06708751618862152, "target_z": -0.18945313127896965, "ce": 5.839932441711426, "genuineness": 4.6705241203308105, "identity": 0.6251290440559387, "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_Intoxication_Altered_States_of_Consciousness/42ea515c27700bee66733c5285adb5d052e3effc9614de89b8d24fdd5ee5b641.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "f9746e8e0954b4b47954a7c547697418212b061a6f9dd658e9a48b2f7f940a0c", "generation_seconds_batch": 16.68161378300283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.010043919086456299, "target_z": -0.3281250100463515, "ce": 6.070269584655762, "genuineness": 4.344170093536377, "identity": 0.5833436250686646, "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_Intoxication_Altered_States_of_Consciousness/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "43d4b4a917c661a396c85a1d36457e3ffebd3f72c8880be9798bd19fbac5bceb", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4139877d899582c327a131e10b7a1b236a41f42693385aa4b42f26c34eaeb404", "generation_seconds_batch": 28.66196233103983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2637183666229248, "target_z": 0.164062518418311, "ce": 5.871703147888184, "genuineness": 4.3504462242126465, "identity": 0.1633172631263733, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/43d4b4a917c661a396c85a1d36457e3ffebd3f72c8880be9798bd19fbac5bceb.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "de7cf4de63030e02f666c7b10b0da00880beb9462890f492873e8daf87b8ae3b", "generation_seconds_batch": 22.877735581016168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.09409761428833, "genuineness": 4.356721878051758, "identity": 0.5165389776229858, "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_Intoxication_Altered_States_of_Consciousness/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "43ec42047393fecc459670cd595a4d9cb9bc05813afcf12aec6266f1b035f36c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6a3588c5aba85d2964778f93ba45b00b5091bbce82e15c71f2b4a21f3281d450", "generation_seconds_batch": 23.57107168796938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04318763315677643, "target_z": -0.23242188546494943, "ce": 6.38003396987915, "genuineness": 4.369274139404297, "identity": 0.5882186889648438, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/43ec42047393fecc459670cd595a4d9cb9bc05813afcf12aec6266f1b035f36c.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "449cfe16882fbb4897a08cf0623090ccec7de99ca0c691f6c3e33f01d16715e7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9b023691ab8493c0971067b61b2cbca723e94eadab1c878a071fb44a469edb68", "generation_seconds_batch": 25.18875556497369, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011683255434036255, "target_z": -0.28906249162804043, "ce": 5.855817794799805, "genuineness": 4.833701133728027, "identity": 0.6157755255699158, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/449cfe16882fbb4897a08cf0623090ccec7de99ca0c691f6c3e33f01d16715e7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "44c40918c241ef671dd3fd3a1e7d8d0817639f81caa602c150afbf579aeec760", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9fd2c3d773e9d25fbc25629703caa6390cdac288b4284a995177c51aeca7a453", "generation_seconds_batch": 23.570920257014222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 5.95112943649292, "genuineness": 4.65797233581543, "identity": 0.5826420783996582, "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_Intoxication_Altered_States_of_Consciousness/44c40918c241ef671dd3fd3a1e7d8d0817639f81caa602c150afbf579aeec760.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "458eae4c47c0078ae6e93a8486936784badf039d96ae8dcb275c0b439c2fb937", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "94e188bb73420ed59eafe1dad05751092c233425d64e6cff984565e19af43902", "generation_seconds_batch": 29.855559173040092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.001353040337562561, "target_z": -0.3124999866048647, "ce": 6.141753673553467, "genuineness": 4.7834930419921875, "identity": 0.7515463829040527, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/458eae4c47c0078ae6e93a8486936784badf039d96ae8dcb275c0b439c2fb937.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "e870ed4984465437649f1f126fe74ebdcd0cb8eebf8dee66d790f6c29bc15c87", "generation_seconds_batch": 18.379555874038488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.356205940246582, "genuineness": 4.268857479095459, "identity": 0.5611783862113953, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, liß 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_Intoxication_Altered_States_of_Consciousness/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "462de1a89f2cd8ba2064be8669f0aa8c533dbdf46aac4f912cd62daace344190", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2d2803661d028f143a39278038c3a096104c28e6848be3679a3d56a2d4e7f8df", "generation_seconds_batch": 28.19265705801081, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014942318201065063, "target_z": -0.2832031379765373, "ce": 6.165581703186035, "genuineness": 4.017816066741943, "identity": 0.30881834030151367, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/462de1a89f2cd8ba2064be8669f0aa8c533dbdf46aac4f912cd62daace344190.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "463005d521a3c23a3e2eb43ab030ad7e2af679ad0c29ee8c69a46428c86b91a9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0776b7810414285dea0a12db44bf0bf454b13e1e1a90c2982f9ccdb9bea0e7b9", "generation_seconds_batch": 26.70265517104417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06274208426475525, "target_z": -0.19726562960457775, "ce": 6.292664527893066, "genuineness": 4.65797233581543, "identity": 0.28097450733184814, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/463005d521a3c23a3e2eb43ab030ad7e2af679ad0c29ee8c69a46428c86b91a9.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "469392ee68a89c64f692bb52020332b3dd6dcab973cbbe221c58d43c3bdba828", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ae0e09f264267cd8c1146f712d038b93539a4ccd6314906922afa4600d6a8736", "generation_seconds_batch": 24.509553702082485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032324060797691345, "target_z": -0.2519531178838344, "ce": 5.831989288330078, "genuineness": 4.494794845581055, "identity": 0.6774920225143433, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/469392ee68a89c64f692bb52020332b3dd6dcab973cbbe221c58d43c3bdba828.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "47347bee7550da4fbbe5643749ca904555eebbbb9375d43c0343a872ee3326cb", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "30358c6dcc5cf85259f1964e7ee48f5935cc93fd54f7a83b53740257f2f64902", "generation_seconds_batch": 17.581461039022543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0024394094944000244, "target_z": -0.3144531312789697, "ce": 6.09409761428833, "genuineness": 4.7458367347717285, "identity": 0.7291446328163147, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/47347bee7550da4fbbe5643749ca904555eebbbb9375d43c0343a872ee3326cb.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "473d052fe0510d7a8dcd38f6699ab9cf7c88cdaf0da7d0ae2ec93a2a35fa7cc8", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "64911bd756e9b50f22e90d8291a299bfd107d6449eb8e0335af3f57cae3f1046", "generation_seconds_batch": 24.2948253309587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04644671082496643, "target_z": -0.22656250502317574, "ce": 6.213237762451172, "genuineness": 4.444586753845215, "identity": 0.4891524612903595, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/473d052fe0510d7a8dcd38f6699ab9cf7c88cdaf0da7d0ae2ec93a2a35fa7cc8.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": "4793c9e8d35e3b2e0341494432c76a6aa48d628bfab8321cfbc7583fc871db76", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "690ea86bf0552c23307d3ca00eff9fa86feff7f418533181cf6fc26f1fb42364", "generation_seconds_batch": 24.87803278095089, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04536035656929016, "target_z": -0.2285156229070101, "ce": 5.80021858215332, "genuineness": 4.6203155517578125, "identity": 0.7331409454345703, "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_Intoxication_Altered_States_of_Consciousness/4793c9e8d35e3b2e0341494432c76a6aa48d628bfab8321cfbc7583fc871db76.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "21cd11bfdb7c9f8c7b6b7dafcc39f6f49a4313bca637d4c9f821fdfbb473e2b0", "generation_seconds_batch": 17.24763520003762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03666949272155762, "target_z": -0.2441406195582263, "ce": 6.24500846862793, "genuineness": 4.720732688903809, "identity": 0.6188291311264038, "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_Intoxication_Altered_States_of_Consciousness/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "47d0f4eb7e6c992095f71c7c9554515273d544e2546ad4d8cd480e030c597266", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "91204490b3341294ea89d4e1b4b1513adcb9ef359b85b026a903bdfaed941347", "generation_seconds_batch": 26.825475313933566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04536035656929016, "target_z": -0.2285156229070101, "ce": 6.109982967376709, "genuineness": 4.494794845581055, "identity": 0.6422210931777954, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/47d0f4eb7e6c992095f71c7c9554515273d544e2546ad4d8cd480e030c597266.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": "48dbb21ff8b28220b9e73b8ff19f01682446d913146af9ab752788325276bd61", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "26e7d3ad2c76aaa29932193410d4e05ba7a8d727c25b58f921aaa8f43635a1b2", "generation_seconds_batch": 24.867930168984458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0475330725312233, "target_z": -0.22460937374420606, "ce": 6.0305562019348145, "genuineness": 4.582659721374512, "identity": 0.7803619503974915, "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_Intoxication_Altered_States_of_Consciousness/48dbb21ff8b28220b9e73b8ff19f01682446d913146af9ab752788325276bd61.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "48f8c3401ed09eb75fe47b3caed397c61e0785e8897f8cb04b9d2d6bec809296", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c2bb5badc0cd57115d21171c9a306f2103e9a77e37fe5778124b9b3fd0eff810", "generation_seconds_batch": 23.451000410947017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007337823510169983, "target_z": -0.2968749899536485, "ce": 5.804190158843994, "genuineness": 4.7081804275512695, "identity": 0.7197662591934204, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/48f8c3401ed09eb75fe47b3caed397c61e0785e8897f8cb04b9d2d6bec809296.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "495b0307accddb9fd9124e7a095cb49f47ae3a2b4c041dbd5263cbbd36a33d4c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3d0ab1a88c157ec4189abea5b8175acdb10ca3f50d28991027de38dd8ac80506", "generation_seconds_batch": 17.73723180696834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.044817179441452026, "target_z": -0.2294921818489273, "ce": 6.173524379730225, "genuineness": 4.331617832183838, "identity": 0.5724070072174072, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/495b0307accddb9fd9124e7a095cb49f47ae3a2b4c041dbd5263cbbd36a33d4c.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": "499ac4be0616ec4d77f6e578d1c787cbb64862f21c98a880dd607d536c5d8c48", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9548fd2376da6804885c6acd7c3c81fe003516269f83555533f5e03c349e1827", "generation_seconds_batch": 24.852782998001203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02580590546131134, "target_z": -0.2636718787673818, "ce": 6.435632705688477, "genuineness": 4.507347106933594, "identity": 0.4251769781112671, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/499ac4be0616ec4d77f6e578d1c787cbb64862f21c98a880dd607d536c5d8c48.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "23e181889f6c1a9d2d7835618b9b34b39f2c4a5bdcff2b1025de9f6df9c2ced8", "generation_seconds_batch": 21.070181149989367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06708751618862152, "target_z": -0.18945313127896965, "ce": 6.117925643920898, "genuineness": 4.369274139404297, "identity": 0.3553122878074646, "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_Intoxication_Altered_States_of_Consciousness/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "4a2cd43815be01d49e011699d4c6aee96cb3fbdb1e80494e1df952b570623361", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8177c5a9fb2b22af215a0932c4b4d83cb84ee802eaf7c49c070242c19c34e462", "generation_seconds_batch": 25.029561156989075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35714516043663025, "target_z": 0.3320312458140202, "ce": 5.855817794799805, "genuineness": 4.545003414154053, "identity": 0.6223209500312805, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/4a2cd43815be01d49e011699d4c6aee96cb3fbdb1e80494e1df952b570623361.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "4a4b2d81e23bcaa064cf78cf0e02fb7b8cbd585744f74084ade116961895629d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "be84f02ac999dd72952af55c49d4b180cfc0f80002b8ae65dc2f6bde9e7a9f05", "generation_seconds_batch": 23.508388133952394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01928776502609253, "target_z": -0.27539061286065863, "ce": 6.086154937744141, "genuineness": 4.306513786315918, "identity": 0.6052554845809937, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/4a4b2d81e23bcaa064cf78cf0e02fb7b8cbd585744f74084ade116961895629d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "4a81845f4bccb4e30b55fdf529ddb8db4466128b3d1516520cfec4a5ba872566", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "bb6df783279c05abe16628d7be9a489720290645e084ddc6efdf89561cd38c68", "generation_seconds_batch": 27.629419628996402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 6.141753673553467, "genuineness": 4.645420074462891, "identity": 0.5328812599182129, "hypothesis": "Ma porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt?", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/4a81845f4bccb4e30b55fdf529ddb8db4466128b3d1516520cfec4a5ba872566.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "4acd2fea8afe8b52df85e3375c584f29edf929b483f14706972d24bc8f52df4a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d4ebbc069e5518741f12b9dae72acf4ff5ced77d67ce9bc2b06115351d903a60", "generation_seconds_batch": 27.260813537985086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0475330725312233, "target_z": -0.22460937374420606, "ce": 5.982900142669678, "genuineness": 4.519899368286133, "identity": 0.5398111343383789, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/4acd2fea8afe8b52df85e3375c584f29edf929b483f14706972d24bc8f52df4a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "4bcfeabc82eb843499f8c5c12f7d9f57e3442305ccc016e37bcea7f432f042c3", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "881e023d4f28f0bdd6c1766fe48099a237d327e7b31c762009d213683e08b44b", "generation_seconds_batch": 23.865155115025118, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04373082518577576, "target_z": -0.2314452997327617, "ce": 6.022613525390625, "genuineness": 4.6956281661987305, "identity": 0.6686267256736755, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/4bcfeabc82eb843499f8c5c12f7d9f57e3442305ccc016e37bcea7f432f042c3.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "4c1aab0e5034e72340ce4b5e43fea8d67c86e13a4815fb2925220a3f6dd518f3", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4967aa5fc2fab9ec3120f96eb6e1e316d4e884f6cbc8c0a2655baaf078ca2b93", "generation_seconds_batch": 23.726914854021743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0236331969499588, "target_z": -0.2675781145350506, "ce": 6.23706579208374, "genuineness": 4.469690799713135, "identity": 0.3732271194458008, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/4c1aab0e5034e72340ce4b5e43fea8d67c86e13a4815fb2925220a3f6dd518f3.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "4c46dfa68eca3bbfea942dce1d04076faf36d9992e4ff03d485619e20924fe23", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "828b3acd7b9b571684eece041b9236b7a5d8e2e2a6132c3b177e42b9ae0de968", "generation_seconds_batch": 16.9591596290702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002992391586303711, "target_z": -0.3046874882792566, "ce": 6.109982967376709, "genuineness": 4.720732688903809, "identity": 0.7455790042877197, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/4c46dfa68eca3bbfea942dce1d04076faf36d9992e4ff03d485619e20924fe23.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": "4c49ba7f9e1111f3a2456d84f7899ec7967f3a147648299a2be5b7ab8dd8cc3c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "99d4867698e307764bcfad7f91f91ca45ca2a56ba45ecb34fba1f4dfd0942488", "generation_seconds_batch": 18.537100233021192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12765198945999146, "target_z": -0.08056640740114444, "ce": 6.1894097328186035, "genuineness": 4.545003414154053, "identity": 0.7662447690963745, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/4c49ba7f9e1111f3a2456d84f7899ec7967f3a147648299a2be5b7ab8dd8cc3c.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "4c6b549cb41c8c5155228d9f0cddc3b5e26f7d9fcce7b28ad97cbbbf1d7f4131", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "74d54e40ecc17306ff991e91f551b06298dd167f17eb87514e380e5bfb59cc6e", "generation_seconds_batch": 27.247857999056578, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014942318201065063, "target_z": -0.2832031379765373, "ce": 6.173524379730225, "genuineness": 4.846253395080566, "identity": 0.49285778403282166, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/4c6b549cb41c8c5155228d9f0cddc3b5e26f7d9fcce7b28ad97cbbbf1d7f4131.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "4d09fc44a76aa0356df022d5840f04f299d003e6d949843fa489f488353061b4", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ac55f240b6b46851f322144c0f2ac801750976f2928b23c82ea455cd5c88a656", "generation_seconds_batch": 24.555406126077287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011683255434036255, "target_z": -0.28906249162804043, "ce": 6.205295085906982, "genuineness": 4.532451152801514, "identity": 0.5306126475334167, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/4d09fc44a76aa0356df022d5840f04f299d003e6d949843fa489f488353061b4.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": "4de847704750894350dac1f01bb68dbb35ef9716b4a54762d89629f6adaea7fe", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a71a8ced3e7a3efb9b3d58def2e59353c95786fff7f04d188606cc3b63e179ed", "generation_seconds_batch": 23.355712009011768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002992391586303711, "target_z": -0.3046874882792566, "ce": 6.062326908111572, "genuineness": 4.645420074462891, "identity": 0.5929059982299805, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/4de847704750894350dac1f01bb68dbb35ef9716b4a54762d89629f6adaea7fe.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "4e03daa6aecc8d994f775ddeeee45ba21c2c1c633d99a4c7785ab7e1a7a681b0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2c6cf5bc69d481569d16641fae981e60f7ec5509b70e604b69c5093fab2404f1", "generation_seconds_batch": 23.19993580505252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0040787458419799805, "target_z": -0.3027343703954222, "ce": 6.022613525390625, "genuineness": 4.934117794036865, "identity": 0.6350131034851074, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/4e03daa6aecc8d994f775ddeeee45ba21c2c1c633d99a4c7785ab7e1a7a681b0.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "4e612c9f4988f8219c332ff83e300a14dcfb6841fcbee7017c484cc6bf26fb09", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f731483a068276b5e2746b3b72c6246eaae033b2ee61724ba5dbb74e1af073c8", "generation_seconds_batch": 24.442077224957757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06491480022668839, "target_z": -0.1933593804417737, "ce": 6.141753673553467, "genuineness": 4.632867813110352, "identity": 0.5783385634422302, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/4e612c9f4988f8219c332ff83e300a14dcfb6841fcbee7017c484cc6bf26fb09.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": "4e9aed6901f8e9d0c24e32ec7c9b60c21675717511b261009a693c017b0cae93", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "066c0fed9feafbd1c49999e049e113fc5c75d4ce3ed91097bfc008f42b023fb8", "generation_seconds_batch": 19.444371746038087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 5.998785495758057, "genuineness": 4.846253395080566, "identity": 0.7660878896713257, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/4e9aed6901f8e9d0c24e32ec7c9b60c21675717511b261009a693c017b0cae93.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "4eac570c4c801609ee272a65d6235456e39e603d287837886bfcf5331cfd11f8", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "03c0f4ea9ca1630b293143928f60a9c9f2a5be6f80430f98dc0ed1b8bcf6903d", "generation_seconds_batch": 17.516305871889926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04536035656929016, "target_z": -0.2285156229070101, "ce": 6.1020402908325195, "genuineness": 4.519899368286133, "identity": 0.44637373089790344, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/4eac570c4c801609ee272a65d6235456e39e603d287837886bfcf5331cfd11f8.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": "4edfc02904946a4d34d890c89280e38baf79c4e962aa4b8196909bfda1b9986a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "5a860aa3d38d87caf133ecad22cecf83a53e054ab434b8d23c655e921a520086", "generation_seconds_batch": 17.668071747990325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34084978699684143, "target_z": 0.3027343703954222, "ce": 5.895530700683594, "genuineness": 4.419482707977295, "identity": 0.38163331151008606, "hypothesis": "De sleutels liggen op de keukentafel. Hij keek in de l 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_Intoxication_Altered_States_of_Consciousness/4edfc02904946a4d34d890c89280e38baf79c4e962aa4b8196909bfda1b9986a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "4ee945aaa57eb5921fd24cbf770c9dab896f2c038d416194a4328f9483bce7cc", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "ea2ac762facacc9fb0bedd4f8668ecca80f32d58a521b801954972124fd49465", "generation_seconds_batch": 24.201847578049637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 6.09409761428833, "genuineness": 4.582659721374512, "identity": 0.49420708417892456, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/4ee945aaa57eb5921fd24cbf770c9dab896f2c038d416194a4328f9483bce7cc.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": "4f281a530e0969b1ab02fdd72f4922f9fc5287161303e74172dff715189568e9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d5340157dfee2adbed29c288cb49c1bdfa95643af60a5f7c77bfe9aaeffbb776", "generation_seconds_batch": 23.073236754047684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01928776502609253, "target_z": -0.27539061286065863, "ce": 6.260893821716309, "genuineness": 4.570107460021973, "identity": 0.4663529396057129, "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_Intoxication_Altered_States_of_Consciousness/4f281a530e0969b1ab02fdd72f4922f9fc5287161303e74172dff715189568e9.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "4f2914facf298ac759f966254d21f846b02168ab44f22d6e4327f958c4d77d27", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "7b7721729af52944f8dea973d3a2407fb2a3edf4068724903d177dfa0088b454", "generation_seconds_batch": 24.73124421504326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017115041613578796, "target_z": -0.279296875418598, "ce": 6.23706579208374, "genuineness": 4.570107460021973, "identity": 0.5088715553283691, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/4f2914facf298ac759f966254d21f846b02168ab44f22d6e4327f958c4d77d27.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "508996f3ecda59c423eb47b5f1c8f993a8f4df0abaa40844f3fb9e4e07f1eb42", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "bbe99e1f9cd7869cc37271db5eeec69facaf8080e9147ad2d205eda3e52f4a12", "generation_seconds_batch": 23.224797858973034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03666949272155762, "target_z": -0.2441406195582263, "ce": 6.173524379730225, "genuineness": 4.268857479095459, "identity": 0.23304149508476257, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/508996f3ecda59c423eb47b5f1c8f993a8f4df0abaa40844f3fb9e4e07f1eb42.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "50e1b332ce12310881683a0b29bfcd1e009fa47037af03fb65b3bee5f2e9d48b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "26f51a45424623ccab7c63a30675532cdd6ad1f9fd675a5afaab9d73772335bf", "generation_seconds_batch": 25.322038265992887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010596886277198792, "target_z": -0.2910156363021454, "ce": 5.855817794799805, "genuineness": 4.1998209953308105, "identity": 0.6124774217605591, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/50e1b332ce12310881683a0b29bfcd1e009fa47037af03fb65b3bee5f2e9d48b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "511e2240f441c3261ce5b03aa740a36127e2361aa13d3b0aad74b36659fa4660", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "458babf51955830e943729c07c97fe188fc773b696230e1b835176ea8814e9e7", "generation_seconds_batch": 17.534334852942266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00516510009765625, "target_z": -0.3007812525115879, "ce": 6.109982967376709, "genuineness": 4.758388519287109, "identity": 0.6563712358474731, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau euh 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_Intoxication_Altered_States_of_Consciousness/511e2240f441c3261ce5b03aa740a36127e2361aa13d3b0aad74b36659fa4660.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "51ea19147c6d2ac099dcb4831a3c392e4a836f0359be31e70e68f45c53383d15", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2936446bb8204fca2b8574e218916189e3868df1beb80e728d89b04bd0cdb903", "generation_seconds_batch": 24.957467517000623, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.040471747517585754, "target_z": -0.2373046801745354, "ce": 6.1020402908325195, "genuineness": 4.381826400756836, "identity": 0.5040982961654663, "hypothesis": "La puerta sigue abierta. He dejado tu abrigue 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_Intoxication_Altered_States_of_Consciousness/51ea19147c6d2ac099dcb4831a3c392e4a836f0359be31e70e68f45c53383d15.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "52737c8efd7dad2901056db99e08a2326be17a70f20f5c226d70d48672d2d5b5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "74c6a2ddf35d76c64b4545c573d34cae695449ac4344356e2b3eed19fec44b34", "generation_seconds_batch": 22.239078488084488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04318763315677643, "target_z": -0.23242188546494943, "ce": 6.332377910614014, "genuineness": 4.306513786315918, "identity": 0.3479815125465393, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/52737c8efd7dad2901056db99e08a2326be17a70f20f5c226d70d48672d2d5b5.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "5346c3a03ac8949c10e69711f2b0c36673c588bc45d706fc4dfc36f614fb9f58", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "75674feae53b9b98ef631ee9b9784bdab744d921958e90b4b306e2e345d56222", "generation_seconds_batch": 17.26262103195768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0019060224294662476, "target_z": -0.3066406329533616, "ce": 6.078212261199951, "genuineness": 4.846253395080566, "identity": 0.6159758567810059, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/5346c3a03ac8949c10e69711f2b0c36673c588bc45d706fc4dfc36f614fb9f58.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "536594bb15ec155dd2dbebe97dda82927bcede85d63ed02d78f47a5905328b42", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "wording", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "da4d25e586e45c2109b402507945297caa8883c89b81eb54cd09cff00a040e5e", "generation_seconds_batch": 17.765737155918032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02146047353744507, "target_z": -0.2714843770929899, "ce": 6.260893821716309, "genuineness": 4.482243061065674, "identity": 0.48196595907211304, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/536594bb15ec155dd2dbebe97dda82927bcede85d63ed02d78f47a5905328b42.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": "539c99c4e5bc786c8ad8ce96153e2b7c88ba40c6a80d355e4607b3891409a433", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "ba36a6bf1f23a5bfedced5f3c97dab911db37ec0d3d474f1d2cb376bd8e53c61", "generation_seconds_batch": 15.97546988306567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06056936830282211, "target_z": -0.2011718787673818, "ce": 5.911416053771973, "genuineness": 4.557555198669434, "identity": 0.714317798614502, "hypothesis": "La carretera irá a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaría al otro lado.", "wer": 0.09523809523809523, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/539c99c4e5bc786c8ad8ce96153e2b7c88ba40c6a80d355e4607b3891409a433.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "54184b59a3487e08b5ada2a992add28f6b6df5169d73fff97b2c83f5f0d3d29d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d662fe73f7a6d65265fdffcf4a3a02bba41bd8044ea17788a63ea6d977028830", "generation_seconds_batch": 22.65052190690767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03666949272155762, "target_z": -0.2441406195582263, "ce": 5.756534099578857, "genuineness": 4.394378662109375, "identity": 0.6466390490531921, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/54184b59a3487e08b5ada2a992add28f6b6df5169d73fff97b2c83f5f0d3d29d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "542cea4f69ecd40a3ae758e11b4e81e76949f4d669c5838fbb306fc5679fd81f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b5fef4dad193806c9ca163698b2470c770d614a228cf6224f260d37e7290ec47", "generation_seconds_batch": 17.17176111205481, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06491480022668839, "target_z": -0.1933593804417737, "ce": 6.078212261199951, "genuineness": 4.494794845581055, "identity": 0.6238074898719788, "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_Intoxication_Altered_States_of_Consciousness/542cea4f69ecd40a3ae758e11b4e81e76949f4d669c5838fbb306fc5679fd81f.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": "5448f5dccf4a5f3c0b7f4c9a5fb958c299e0f171b76ed2d91331baeb9da1390d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3ed639b017a5503552d30f2d1c41125f04ff592438146e82fb34aad2f30fade5", "generation_seconds_batch": 18.416026331018656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 6.0305562019348145, "genuineness": 4.645420074462891, "identity": 0.5501714944839478, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí junto junto a la estantería alta. La colocaremos después de comer.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/5448f5dccf4a5f3c0b7f4c9a5fb958c299e0f171b76ed2d91331baeb9da1390d.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "e9ea0fd720315fa8f47fbf9473b750606f1c744132eecd8324207de502eddd02", "generation_seconds_batch": 18.379555874038488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.000819668173789978, "target_z": -0.308593750837196, "ce": 6.24500846862793, "genuineness": 3.9173994064331055, "identity": 0.6389721035957336, "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_Intoxication_Altered_States_of_Consciousness/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "550c4f421005c9f661bd6044f8377272e01e460b367b292d637a0c91050a77f3", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "20a66e37121438ba0ffa3d5c2da7065f7279b39fa19337b274ca330d2c3874d7", "generation_seconds_batch": 24.36711001896765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.040471747517585754, "target_z": -0.2373046801745354, "ce": 6.324435234069824, "genuineness": 4.7332844734191895, "identity": 0.36603155732154846, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/550c4f421005c9f661bd6044f8377272e01e460b367b292d637a0c91050a77f3.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "55df35edf08eb476746197665107514753bed056bca0cc1dea328d809146564a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1dfb8c27ea3637284038041eb6c4e67622332a0ab4709e19770593f366ccea9b", "generation_seconds_batch": 24.170163747039624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 6.348263263702393, "genuineness": 4.425758361816406, "identity": 0.4109383821487427, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/55df35edf08eb476746197665107514753bed056bca0cc1dea328d809146564a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "56074275e26fce5dd9c945c4d4254c0fb1d6a26ae8fd2767df397c8038ca92de", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f5df10edd304b92ffe9c58f0e698ca568e1bbcf584829efedafa7246f5dd784a", "generation_seconds_batch": 23.726914854021743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 6.181467056274414, "genuineness": 4.7081804275512695, "identity": 0.6533646583557129, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/56074275e26fce5dd9c945c4d4254c0fb1d6a26ae8fd2767df397c8038ca92de.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "563cecba1ccb4885a2a10280ec57ea73ef55471599e9faf003e14e9aa9db9672", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8e9f0094d6656f2a362f8865e5b4a6556356c4e86a494732b32c21c14481242c", "generation_seconds_batch": 28.60933845001273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04807624965906143, "target_z": -0.2236328148022889, "ce": 6.1020402908325195, "genuineness": 4.507347106933594, "identity": 0.3274909257888794, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/563cecba1ccb4885a2a10280ec57ea73ef55471599e9faf003e14e9aa9db9672.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "56607df3ccceb688a31ad84db190fd81be5d11be9a499b4012dbdf7344c59d2e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3b40f562218e35834eb82be094ff47def594ff63dd3a14559a739ddc81c95fad", "generation_seconds_batch": 22.64642169396393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033410415053367615, "target_z": -0.25, "ce": 6.475345611572266, "genuineness": 4.494794845581055, "identity": 0.550363302230835, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/56607df3ccceb688a31ad84db190fd81be5d11be9a499b4012dbdf7344c59d2e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "56ed72ac01b374772fb6c6f884bfd1c67beeda379a51158d364953595d234ee2", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1106525db8fa1522c497530271a267619125c8a6a7ecc165b742cb3529f9e31d", "generation_seconds_batch": 24.27008806192316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0002666860818862915, "target_z": -0.3105468687210303, "ce": 6.197352409362793, "genuineness": 4.607763767242432, "identity": 0.7736666202545166, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/56ed72ac01b374772fb6c6f884bfd1c67beeda379a51158d364953595d234ee2.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "57485b0061510c9587817faf2733143e478ff9eb41fc2cdb3fea38033df73a90", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "56ce166792ae564d1eeab0dc3995242ab12408b23eb3889c6cefc16c58e9717f", "generation_seconds_batch": 25.081723792944103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17742078006267548, "target_z": 0.008911140530400206, "ce": 6.0305562019348145, "genuineness": 4.582659721374512, "identity": 0.650188684463501, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/57485b0061510c9587817faf2733143e478ff9eb41fc2cdb3fea38033df73a90.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": "57726f8387564b0917bb878da3d98eff10d731ec7f5a97ab84d7764d56165d33", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d49daf9204545bdfa9c16d24892a4d2b1e81fdf29e0b886417013dcb11e53cdf", "generation_seconds_batch": 26.3502779599512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03938537836074829, "target_z": -0.23925782484864033, "ce": 5.7684478759765625, "genuineness": 4.6956281661987305, "identity": 0.8182888031005859, "hypothesis": "Les clés sont sur la table de la cuisine J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/57726f8387564b0917bb878da3d98eff10d731ec7f5a97ab84d7764d56165d33.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "57eb4b716dc2bdd46af4180510e446793c82854d42ce98638a5581fa43da1fb1", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "6930fb07d03e6a9eb8726de6051ccf19762c4cf62f3b22ee28e2c63759d16aa2", "generation_seconds_batch": 25.580453987931833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06165573000907898, "target_z": -0.19921874748841215, "ce": 6.141753673553467, "genuineness": 4.570107460021973, "identity": 0.7360591888427734, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/57eb4b716dc2bdd46af4180510e446793c82854d42ce98638a5581fa43da1fb1.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "57fdc5267f24759443254178e38d9194382954eecbaf4c71d2298e77760f0981", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0758d80510d98940b0577e8ce9e6900e2a59f7d56b638ab47e3f193ef63a49a6", "generation_seconds_batch": 23.780435819062404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 6.332377910614014, "genuineness": 4.582659721374512, "identity": 0.551908016204834, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/57fdc5267f24759443254178e38d9194382954eecbaf4c71d2298e77760f0981.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "582d7a0610f8562b0ab201f140392234c331044183d5bc11bfcfb280048d532c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "a4bd2917e23ee4ffd96904828a986b3c73cbf379896e982883338ac31d9642c2", "generation_seconds_batch": 24.584586452925578, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.0146708488464355, "genuineness": 4.65797233581543, "identity": 0.6332027912139893, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/582d7a0610f8562b0ab201f140392234c331044183d5bc11bfcfb280048d532c.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "58480a9bea56aae852b42d25265882e58ba17de8c1827e61cfb066596b0078c8", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "71b2b931714ba4bf6e3432f6c4a78b034792aa8fc6504406282024e39595797f", "generation_seconds_batch": 23.544562345021404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06437162309885025, "target_z": -0.1943359393836909, "ce": 6.292664527893066, "genuineness": 4.632867813110352, "identity": 0.7025865912437439, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/58480a9bea56aae852b42d25265882e58ba17de8c1827e61cfb066596b0078c8.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "58778c2d936c1a43cbc0fc82e87ebf8602554cc316410a7f60c01583f50d82b7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a1dcde74d96bc57a8c839e09117610f8ca900f5683a8fe4c502605abd1ab9c00", "generation_seconds_batch": 22.764274138957262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.005698487162590027, "target_z": -0.3203125117207434, "ce": 6.09409761428833, "genuineness": 4.582659721374512, "identity": 0.4363821744918823, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/58778c2d936c1a43cbc0fc82e87ebf8602554cc316410a7f60c01583f50d82b7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "58bc0919d5eaf8b9e3437280f41c1c7f744f366b6c4a5e423e4a6e58e71de43f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "09995c4e52b12681ab80db97eeeb5631f66a018c9e5be0932a1c02085b75797c", "generation_seconds_batch": 24.303023175918497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06708751618862152, "target_z": -0.18945313127896965, "ce": 6.4515180587768555, "genuineness": 4.65797233581543, "identity": 0.21147963404655457, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/58bc0919d5eaf8b9e3437280f41c1c7f744f366b6c4a5e423e4a6e58e71de43f.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "58e0486fb5bf640cdf5ef38accd1d72ee4b0cc893ef205ce21f76a66ce982c3d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "55131115965832ab959a66a29e6e0feff32f6a3bd6b318f4ca0f8ae9579b5ab2", "generation_seconds_batch": 26.7967649360653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10130780190229416, "target_z": -0.12792969022088685, "ce": 6.213237762451172, "genuineness": 4.356721878051758, "identity": 0.6172366142272949, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/58e0486fb5bf640cdf5ef38accd1d72ee4b0cc893ef205ce21f76a66ce982c3d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "58f5efe180d014462378c53a19934dcc543ff6633f6559139f7c20df37c4c7f1", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2b85f213ff7e25cb8ba1a734ae93595313051db6f4e17e252a825d524f35c0ba", "generation_seconds_batch": 23.220441650017165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05024896562099457, "target_z": -0.21972656563948484, "ce": 6.054384231567383, "genuineness": 4.319066047668457, "identity": 0.4222603440284729, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/58f5efe180d014462378c53a19934dcc543ff6633f6559139f7c20df37c4c7f1.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": "592219919f7f020edcd134a4080267cce8aad88b4ffe670080ae8ec9292be097", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "d05fe658e13abad557bebac6850c4bc9f4aa7b7a0600ca349341f3c52bc165d8", "generation_seconds_batch": 17.319464911008254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0763215646147728, "target_z": -0.172851562290701, "ce": 5.395142555236816, "genuineness": 4.607763767242432, "identity": 0.7498166561126709, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lais-le bien et vérifié les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/592219919f7f020edcd134a4080267cce8aad88b4ffe670080ae8ec9292be097.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "59fc4b45d2213ff23bf8f7eeae1eebb0221c6c6ce6cf9d33fb8b2e1cd87bbf8c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3712f2e88c9cdc01c1acefda6a3ecce59ac8dcfb01b625da9285fb000244116a", "generation_seconds_batch": 23.852023339946754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03558313846588135, "target_z": -0.24609373744206067, "ce": 6.157639026641846, "genuineness": 4.457139015197754, "identity": 0.6953390836715698, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/59fc4b45d2213ff23bf8f7eeae1eebb0221c6c6ce6cf9d33fb8b2e1cd87bbf8c.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "5a658c6d4d15bec7218eaccbda681b817dcb0890055224cce059451de0b03dd8", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "cb98e0f428b28ac902355e913fb0f53c7e076135e113cfbe0b6d5982b238ef8b", "generation_seconds_batch": 23.277833850006573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04644671082496643, "target_z": -0.22656250502317574, "ce": 5.974957466125488, "genuineness": 4.18726921081543, "identity": 0.4857599139213562, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/5a658c6d4d15bec7218eaccbda681b817dcb0890055224cce059451de0b03dd8.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "5ab618b82e97b279d0d146757d6edee541d84980980a196ef1a08d25a27f9413", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1d3015af60061b1f560c3213178ee45956487e76e6ae78111b4e278fa62be03d", "generation_seconds_batch": 22.64112412300892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032324060797691345, "target_z": -0.2519531178838344, "ce": 6.117925643920898, "genuineness": 4.909013748168945, "identity": 0.8617063760757446, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/5ab618b82e97b279d0d146757d6edee541d84980980a196ef1a08d25a27f9413.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "5bf142edcbb7d04af2e08e98ef14ff97921d01900a01d95e6538bf7f3db266c3", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c395e7acf4492ee8b2fbdf0eecf5972d2636466a5b9f8abaa9b06c1733d516b9", "generation_seconds_batch": 17.43831864092499, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030151337385177612, "target_z": -0.2558593804417737, "ce": 6.23706579208374, "genuineness": 4.595211505889893, "identity": 0.5509018898010254, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/5bf142edcbb7d04af2e08e98ef14ff97921d01900a01d95e6538bf7f3db266c3.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "5c77c3a1b5c37896a95bd81afc3fc04b244fe925539b0bc9bbf489fab3bf16af", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8db2349fc3a653cf430c710116ef3fcb6ecda04c0bc5edf1822c00c6d540d435", "generation_seconds_batch": 18.364523895084858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.0146708488464355, "genuineness": 4.946669578552246, "identity": 0.7126457691192627, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/5c77c3a1b5c37896a95bd81afc3fc04b244fe925539b0bc9bbf489fab3bf16af.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "5cf75fbcb8a734a48e6b101b8630226e3500f2e1371df212c8a498254bfabf73", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "31491d1bc823a21bb1df4a62f8640a762ba3c58c0fd0cedeec4c1b6fe96b6c8f", "generation_seconds_batch": 17.209769928944297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 5.9431867599487305, "genuineness": 4.7834930419921875, "identity": 0.6190302968025208, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/5cf75fbcb8a734a48e6b101b8630226e3500f2e1371df212c8a498254bfabf73.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "5d01e6793fc7edb10142dc379cb7ff13e9a104e0d340db342636505087a4e3fa", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "96a64bc0f317edfac580c9a2cdc882ad15c3fe5a637b3ff8e8ced098f6a773d7", "generation_seconds_batch": 17.43831864092499, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03503994643688202, "target_z": -0.24707032317424843, "ce": 6.308549880981445, "genuineness": 4.68307638168335, "identity": 0.28209352493286133, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/5d01e6793fc7edb10142dc379cb7ff13e9a104e0d340db342636505087a4e3fa.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": "5d76e4184f1d75fef2611d107e1df67988dce8eb57ba60040bd8f50dbd2b7d8b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "f52cd5fc4e59633b5854c71e6ddc6ead45528f74149c64dc76cd0cbb6c650777", "generation_seconds_batch": 17.11550425796304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03829902410507202, "target_z": -0.2412109427324747, "ce": 6.125868320465088, "genuineness": 4.607763767242432, "identity": 0.5382508039474487, "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_Intoxication_Altered_States_of_Consciousness/5d76e4184f1d75fef2611d107e1df67988dce8eb57ba60040bd8f50dbd2b7d8b.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "95ad52cfdc256f124e1f127fad98516b5b5aa914b2ed9ef348fd0826b6938513", "generation_seconds_batch": 17.70324590196833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.133810997009277, "genuineness": 4.432034492492676, "identity": 0.8179551362991333, "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_Intoxication_Altered_States_of_Consciousness/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.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": "5eae908095f6482d9452c442623b5765563049177c0e2a2cdccec0a3582efe49", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "d8fbf723cce04949066ca047addda0fbee40b733d077e4035bb94a9a0a14a6d7", "generation_seconds_batch": 24.219618072966114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32346805930137634, "target_z": 0.2714843770929899, "ce": 6.062326908111572, "genuineness": 4.369274139404297, "identity": 0.7996879816055298, "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_Intoxication_Altered_States_of_Consciousness/5eae908095f6482d9452c442623b5765563049177c0e2a2cdccec0a3582efe49.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "5f592a46a82606ac35511860813674859c5eb7567ce7307aec7af4cb47b91fb5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c335f21707cabd8a17285f25b4830ce603871eedc74a98c89f4b7018870630db", "generation_seconds_batch": 25.244485217961483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03938537836074829, "target_z": -0.23925782484864033, "ce": 6.173524379730225, "genuineness": 4.507347106933594, "identity": 0.23155751824378967, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/5f592a46a82606ac35511860813674859c5eb7567ce7307aec7af4cb47b91fb5.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "6109ac190632c18c877aa05d0d3d404251c8c4cdcce06ddb2fff4698746a22da", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8df1a338d1adfbf3dbdfc89d8e38c459065928fff8dbda1590b2912dcd36e75f", "generation_seconds_batch": 23.228618724970147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16526713967323303, "target_z": -0.012939459560943901, "ce": 6.078212261199951, "genuineness": 4.582659721374512, "identity": 0.7068724632263184, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/6109ac190632c18c877aa05d0d3d404251c8c4cdcce06ddb2fff4698746a22da.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "61318b3a0d5407f2c6a4b0c970b2fc611f76dd0c65ade890bf185ce283513684", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f7851dfc784ad268916b8adba5d6897b7427f5be9e7bdac404283d4e7b428b7b", "generation_seconds_batch": 18.51549864804838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05024896562099457, "target_z": -0.21972656563948484, "ce": 5.744620323181152, "genuineness": 4.808597087860107, "identity": 0.7171622514724731, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/61318b3a0d5407f2c6a4b0c970b2fc611f76dd0c65ade890bf185ce283513684.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "6134b0a80686cf70b607cfea662777c0c913e3ea19384faacd53885fc17a9f0f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7ea648a92c973ad2070b894bac69ea79180c69ba410bfd92e2459a5a3808b7ac", "generation_seconds_batch": 16.940183316008188, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02146047353744507, "target_z": -0.2714843770929899, "ce": 6.062326908111572, "genuineness": 4.7332844734191895, "identity": 0.646714985370636, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/6134b0a80686cf70b607cfea662777c0c913e3ea19384faacd53885fc17a9f0f.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "613cb63910514c0f2d12dab1e7d7b66007cb08305e7d0796a2d6ac411a23967c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d20758356e0f123eb839f8c285f500f3832fff6fe6b731c9dee2d5cd42cc9019", "generation_seconds_batch": 23.887682396103628, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.403861999511719, "genuineness": 4.7834930419921875, "identity": 0.6098843216896057, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/613cb63910514c0f2d12dab1e7d7b66007cb08305e7d0796a2d6ac411a23967c.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": "61ff44766e4e789ff46f0323a6a6451524d0c78c29696bf236607f6c6090f095", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "ac4c20c85f0feabc0d4e154e4bee41532f9f40e181e11ed9dd8cd1f3c6c81d98", "generation_seconds_batch": 17.20409497898072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 6.1894097328186035, "genuineness": 4.595211505889893, "identity": 0.26505541801452637, "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_Intoxication_Altered_States_of_Consciousness/61ff44766e4e789ff46f0323a6a6451524d0c78c29696bf236607f6c6090f095.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "62311b18c158aae8273a35d8bbc4be0016d0602bef3f97c11def76217a69f18e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "191e93d2147524f0957d62629b124af3b0d764424059c8399801caffe1d3df4f", "generation_seconds_batch": 17.73723180696834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03775584697723389, "target_z": -0.2421875016743919, "ce": 6.125868320465088, "genuineness": 4.482243061065674, "identity": 0.4974624514579773, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/62311b18c158aae8273a35d8bbc4be0016d0602bef3f97c11def76217a69f18e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "62585909429780cf2fc73bb4d308047ff4f4d20218ed5c3b18cf0fad176cdfa1", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7c7a6131d7bff6ada60c9f4b588ec86d3af2fed4142316e5f04fa79111abe7af", "generation_seconds_batch": 24.957467517000623, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 5.796247482299805, "genuineness": 3.8671910762786865, "identity": 0.5781406760215759, "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_Intoxication_Altered_States_of_Consciousness/62585909429780cf2fc73bb4d308047ff4f4d20218ed5c3b18cf0fad176cdfa1.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "62c9b3e4459616af516f922c35d8c02dad2e65e4f3deb63cb948344e1587df0c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "14d70cfb9796ccf48c8b235d68b0177c99ee5aedd64f35b902ff9e4256419f6e", "generation_seconds_batch": 23.370806023012847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.181467056274414, "genuineness": 4.7081804275512695, "identity": 0.4677259922027588, "hypothesis": "I found the little box it was beside the old window. I can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/62c9b3e4459616af516f922c35d8c02dad2e65e4f3deb63cb948344e1587df0c.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "630c884e17871e636d0283608f5a12f2b2c86c74b9804553db65a4e6462469b1", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "aa981ba5ed2c409bfe6c935b2559d9636af8e525412e269d5d5091a4a387e24b", "generation_seconds_batch": 28.10403846995905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0019060224294662476, "target_z": -0.3066406329533616, "ce": 6.086154937744141, "genuineness": 4.570107460021973, "identity": 0.4669564366340637, "hypothesis": "Die Tür ist noch offen? Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/630c884e17871e636d0283608f5a12f2b2c86c74b9804553db65a4e6462469b1.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": "63274b422c9765d9bf70ef31bdc7a16f79edce127c2abe34ad443584c3cdb824", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "80bf5da8cb6b8b57aa016b10ea62b4cf994be7487651e78c75e723e790c0587f", "generation_seconds_batch": 18.116234724991955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 6.316492557525635, "genuineness": 4.519899368286133, "identity": 0.2616645097732544, "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_Intoxication_Altered_States_of_Consciousness/63274b422c9765d9bf70ef31bdc7a16f79edce127c2abe34ad443584c3cdb824.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "6358475f114513c41ae55b54a119c0874ba32e61406b1d61e91af140b03aad67", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "879ea258b80039ad220b6029f7f0f9b1907a7852885c57b7532d671a40182611", "generation_seconds_batch": 17.00764268299099, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11380092799663544, "target_z": -0.1054687407908445, "ce": 5.974957466125488, "genuineness": 4.287685871124268, "identity": 0.619159460067749, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/6358475f114513c41ae55b54a119c0874ba32e61406b1d61e91af140b03aad67.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "635b9924bd27a5543c823ed6728d5684d937fe8914678752941435a7ad09a74a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "9fb210a14933e517f9658431fc89196431aa67c991c3a4a014068ff244877b2b", "generation_seconds_batch": 22.808710046927445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03775584697723389, "target_z": -0.2421875016743919, "ce": 5.990842819213867, "genuineness": 4.3504462242126465, "identity": 0.2906861901283264, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/635b9924bd27a5543c823ed6728d5684d937fe8914678752941435a7ad09a74a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "63665130b4735cfbb28ecff63f1c4986a8fe3ed59ce3a139b022c10895142d84", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5b6f020b0ee83d925de54819b88d7864e7917f4bbe3d91b4028c8b9e3249c39b", "generation_seconds_batch": 27.247857999056578, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 6.252951145172119, "genuineness": 4.846253395080566, "identity": 0.7178992033004761, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/63665130b4735cfbb28ecff63f1c4986a8fe3ed59ce3a139b022c10895142d84.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "6480eaac0e6f20611772e30ab9a3b38fc6affe5266c1abe8768f5adf15a341e3", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9b39c8bfa45c3e9f9f1b9e5b1453f5488f757bcbe2b9674ebd0ee554747f672f", "generation_seconds_batch": 22.292830382939428, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0507921427488327, "target_z": -0.21875000669756764, "ce": 5.720792293548584, "genuineness": 4.758388519287109, "identity": 0.8088306188583374, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/6480eaac0e6f20611772e30ab9a3b38fc6affe5266c1abe8768f5adf15a341e3.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "648e03d50cbe1a84e46ebe7744d034df933c3855e0464e84ce68c4c84fb5bcad", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "575c3da47099ba5159b4d05563bf98324f6feba86619655116759f15ee85f5fd", "generation_seconds_batch": 26.063175354967825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.046989887952804565, "target_z": -0.22558594608125854, "ce": 6.268836498260498, "genuineness": 4.7332844734191895, "identity": 0.5607680082321167, "hypothesis": "Ich habe die kleine Schacht gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/648e03d50cbe1a84e46ebe7744d034df933c3855e0464e84ce68c4c84fb5bcad.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "649089650d2b26f2d2395d048bbbe93cb5cc20ad650340afd3ac6bd1c684309b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d3d61befc58d81e44da558b752a8812ce52599e434557e577f1db24d7dc7d39c", "generation_seconds_batch": 22.78294626902789, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0019060224294662476, "target_z": -0.3066406329533616, "ce": 5.7684478759765625, "genuineness": 4.457139015197754, "identity": 0.5160604119300842, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/649089650d2b26f2d2395d048bbbe93cb5cc20ad650340afd3ac6bd1c684309b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "64e8faced653d01e956e7d9764648db576b9fc2acb6c6e53973be1813df265bc", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bd8ee1635cfeea0fcd1a8d1695b2206a493a6e71ec47fa3d27e82ed2347b8b1f", "generation_seconds_batch": 27.793263258994557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031237691640853882, "target_z": -0.2539062625579393, "ce": 6.213237762451172, "genuineness": 4.7332844734191895, "identity": 0.6655330061912537, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/64e8faced653d01e956e7d9764648db576b9fc2acb6c6e53973be1813df265bc.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": "64ff972565f044a99d38b7e9d24ee994064e2cf135c8b07b736bf074cd4e95ec", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b334fee600ac0d436c9f7fea996fbc01a05694f4186d6a7b84bb0b55307df506", "generation_seconds_batch": 23.310212840908207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06926023960113525, "target_z": -0.18554686872103035, "ce": 6.070269584655762, "genuineness": 4.808597087860107, "identity": 0.714015781879425, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich lass sie zweimal, dann leg dich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.125, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/64ff972565f044a99d38b7e9d24ee994064e2cf135c8b07b736bf074cd4e95ec.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": "657cb5210dbed39ceb0847198c4930c5a54dc3d97a9c0e907a3e064b4b2487bb", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "88b3ac5d661d703775ec8cbdb14bf34f48d12b94592112a3c0482fad738a6b96", "generation_seconds_batch": 17.20409497898072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02689225971698761, "target_z": -0.2617187608835474, "ce": 6.300607204437256, "genuineness": 4.532451152801514, "identity": 0.7019087076187134, "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_Intoxication_Altered_States_of_Consciousness/657cb5210dbed39ceb0847198c4930c5a54dc3d97a9c0e907a3e064b4b2487bb.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "65c054620905fffcf8ef9a425d9708de819c3babe974338eaa613be50cada66e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "800870487d7f250bb794d80a7441e40939ebe05fedbed3a2c13eae55c505ffc2", "generation_seconds_batch": 24.657100228010677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007337823510169983, "target_z": -0.2968749899536485, "ce": 6.38797664642334, "genuineness": 4.758388519287109, "identity": 0.5609031915664673, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/65c054620905fffcf8ef9a425d9708de819c3babe974338eaa613be50cada66e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "66b17133a00307611450d668d1becf431ab9122173470ef4ecd7f9eab8731281", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "16a287f88458202dda13cbe1fed68d89f34978365c2e0a1459033acc22288ace", "generation_seconds_batch": 32.46501441707369, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04427400231361389, "target_z": -0.2304687407908445, "ce": 6.046441555023193, "genuineness": 4.758388519287109, "identity": 0.6532101631164551, "hypothesis": "Die Tür 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_Intoxication_Altered_States_of_Consciousness/66b17133a00307611450d668d1becf431ab9122173470ef4ecd7f9eab8731281.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "66e0e7b0c0b6dd28641d128504afd295823601f4b8976f8be7d961a8ebfe843c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "76228a23e00b49b2c2d75c00961339b86b042d833991392cf9ce8b70b9c7353a", "generation_seconds_batch": 17.563004769966938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 6.308549880981445, "genuineness": 4.7081804275512695, "identity": 0.36554601788520813, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/66e0e7b0c0b6dd28641d128504afd295823601f4b8976f8be7d961a8ebfe843c.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "678eae3b1f4939c7b620448697ed76bbbec8528b1498091cc8624792c4ab8f9b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e92b8952fa92485b332f16965cfe77eba270015547e4051b142948729f7c520b", "generation_seconds_batch": 25.24216433498077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008424177765846252, "target_z": -0.2949218720698142, "ce": 6.070269584655762, "genuineness": 4.406930446624756, "identity": 0.8208010792732239, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/678eae3b1f4939c7b620448697ed76bbbec8528b1498091cc8624792c4ab8f9b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "679238d9b4ba3023f8eb2c29a5fb002c3e3fdb0c2380324e52d2cdc026543aec", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ba0b66d412e353568b63d304bff9afe5c869ae1a3a05d6dd385a1657f5a61350", "generation_seconds_batch": 22.764274138957262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00516510009765625, "target_z": -0.3007812525115879, "ce": 6.09409761428833, "genuineness": 4.7332844734191895, "identity": 0.6519007682800293, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/679238d9b4ba3023f8eb2c29a5fb002c3e3fdb0c2380324e52d2cdc026543aec.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "6793270d159f4be2da7703cd217146bf46789c7de3854b389b841ce35b1abf4c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3e0a5af5d0b5cbf98ed25bb1f3dcd1b18afc4ab19866098896e9b9bf082c0c1e", "generation_seconds_batch": 27.106877909973264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030151337385177612, "target_z": -0.2558593804417737, "ce": 6.300607204437256, "genuineness": 4.507347106933594, "identity": 0.7308840751647949, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/6793270d159f4be2da7703cd217146bf46789c7de3854b389b841ce35b1abf4c.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": "67ac17c3b3461436e10711f89a0f7e9c2d8d3540775a3011669c15267a872dfc", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "594e406eb622f5af0f71e2a7794bb098e063e252356e60bb859a3fc82c3f2000", "generation_seconds_batch": 17.747690104995854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03612631559371948, "target_z": -0.2451171785001435, "ce": 6.284721851348877, "genuineness": 4.344170093536377, "identity": 0.4452405571937561, "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_Intoxication_Altered_States_of_Consciousness/67ac17c3b3461436e10711f89a0f7e9c2d8d3540775a3011669c15267a872dfc.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "67d52a9ab50ded196462be6c3b9758889a5242efdc1c4399f328ae995bd8fa51", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e0ff752a094ee60a648589fd8cd15cbbf7f19d09fe857537f6d6c297ccbf4096", "generation_seconds_batch": 25.544484158977866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04861942678689957, "target_z": -0.2226562558603717, "ce": 6.300607204437256, "genuineness": 4.645420074462891, "identity": 0.2709026336669922, "hypothesis": "I found the little box. It was beside the old window. We can look inside together?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/67d52a9ab50ded196462be6c3b9758889a5242efdc1c4399f328ae995bd8fa51.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "684b6f2a5e3c04c2a15e49749a9be95e80b38b47918d0b94ed4c034b5000380c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "76a1b8d3bd8dd54b2d8a6dad0e5b3144e4d8c37164f52e7509fae6198aae373d", "generation_seconds_batch": 26.214998690993525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08772832900285721, "target_z": -0.1523437441396283, "ce": 5.935244083404541, "genuineness": 4.356721878051758, "identity": 0.5847316980361938, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/684b6f2a5e3c04c2a15e49749a9be95e80b38b47918d0b94ed4c034b5000380c.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "697cf5b704f57ef769e45f5e5afbee46acbeda154c8c415fe0a0b68bae9056ac", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1752423f2f87cc2e47242256d1f3d3f84df70fa62790c9b39d8a353921b90b35", "generation_seconds_batch": 22.60465033503715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09044422209262848, "target_z": -0.1474609360349071, "ce": 5.967014789581299, "genuineness": 4.457139015197754, "identity": 0.47183865308761597, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/697cf5b704f57ef769e45f5e5afbee46acbeda154c8c415fe0a0b68bae9056ac.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": "6a0354a66f3f29c09c31a04dde9dac31d2df12785c5f97627ddd470380d76be1", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "15cb2e86d124378176ac4e669155b9e893a2490e13dab5521bbeede96340d604", "generation_seconds_batch": 18.515709316008724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0779511034488678, "target_z": -0.16992187206981416, "ce": 6.213237762451172, "genuineness": 4.808597087860107, "identity": 0.450591504573822, "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_Intoxication_Altered_States_of_Consciousness/6a0354a66f3f29c09c31a04dde9dac31d2df12785c5f97627ddd470380d76be1.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "bcc8310a59bb8ac99182c73d94b38fd8d953b122a79336bad5b350d1e027bdc3", "generation_seconds_batch": 19.38186053710524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.021993860602378845, "target_z": -0.34960938713934137, "ce": 6.4515180587768555, "genuineness": 3.7793264389038086, "identity": 0.2855831980705261, "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_Intoxication_Altered_States_of_Consciousness/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "6b3e96b3e53acac9e9f2c1551c17bde6414905922772dfcafff81644bd06a1e9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6247af8ec3363b234599a02ae1fa988a37734a532c6f2c598169470c01496a35", "generation_seconds_batch": 24.293421749025583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010596886277198792, "target_z": -0.2910156363021454, "ce": 5.967014789581299, "genuineness": 4.632867813110352, "identity": 0.7630019783973694, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/6b3e96b3e53acac9e9f2c1551c17bde6414905922772dfcafff81644bd06a1e9.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": "6b62dad90a471558aa607d2164bb4d8e37b07f889f257ac51283cb69a30278d6", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "7c905ec69a904031a975835dce6620b988b845f1dacc484e048f0898f5e63a6b", "generation_seconds_batch": 19.196042916970327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06328526884317398, "target_z": -0.1962890572675253, "ce": 5.927301406860352, "genuineness": 4.7332844734191895, "identity": 0.6345423460006714, "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_Intoxication_Altered_States_of_Consciousness/6b62dad90a471558aa607d2164bb4d8e37b07f889f257ac51283cb69a30278d6.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "95e09d6aee75b5926b80ef45d8cd79eabeebbd3387fb9c4db03f483d2ca38500", "generation_seconds_batch": 22.877735581016168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030151337385177612, "target_z": -0.2558593804417737, "ce": 6.229123115539551, "genuineness": 4.758388519287109, "identity": 0.6273757815361023, "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_Intoxication_Altered_States_of_Consciousness/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "6bdfed7c90b1fdf606c0041dd86ac3f03fac03fd903ef795d2f5d6b0e13f996d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8447800ca8662babcbf78a9548af96bf7809434f13382e1342520356833dcd37", "generation_seconds_batch": 16.810929256957024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 6.054384231567383, "genuineness": 4.833701133728027, "identity": 0.7978121042251587, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/6bdfed7c90b1fdf606c0041dd86ac3f03fac03fd903ef795d2f5d6b0e13f996d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "6bfe336aa38e11e395993a64b885583358d76584369e563e0c1b3ab8a1c68a8a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "94b8c3e2925ff664c4dad405f4f94b0d3880c030c024f0d39b490fd66703c5b6", "generation_seconds_batch": 19.981276196893305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04318763315677643, "target_z": -0.23242188546494943, "ce": 5.967014789581299, "genuineness": 4.645420074462891, "identity": 0.8177801370620728, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/6bfe336aa38e11e395993a64b885583358d76584369e563e0c1b3ab8a1c68a8a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "6c3723c2d0162bcc7c392fd8d046c16544577a9692b7964c8a0cd51913793f4a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6319e2d26c9b26f55bd05c6d73aad5d09cb95b181d57eea3e6aa431c235d7603", "generation_seconds_batch": 26.64299234491773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02146047353744507, "target_z": -0.2714843770929899, "ce": 6.078212261199951, "genuineness": 4.645420074462891, "identity": 0.6578253507614136, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/6c3723c2d0162bcc7c392fd8d046c16544577a9692b7964c8a0cd51913793f4a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "6c444a29c185461401be9dc6b207553eddd62487e30f9101bdb20715cf7c461f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "159629c32ad2f006a898a073e1faac81227aeb34189f06fc4317f5e84d92fd6b", "generation_seconds_batch": 17.87886647193227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06654433906078339, "target_z": -0.19042969022088685, "ce": 5.649308204650879, "genuineness": 4.607763767242432, "identity": 0.5634682178497314, "hypothesis": "Die Tür ist noch offen. Ich habe dein Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/6c444a29c185461401be9dc6b207553eddd62487e30f9101bdb20715cf7c461f.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": "6c848c417803a9e3ba4d72fbaab70dd9964bec399f0c58c70c0cf0e89327b39c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "bc8dfa41f8b8f3e7262afdf2b31e3b21b3990703bf8364f5511c26ac79cfe23a", "generation_seconds_batch": 15.979272366967052, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.046989887952804565, "target_z": -0.22558594608125854, "ce": 5.982900142669678, "genuineness": 4.6956281661987305, "identity": 0.7570832967758179, "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_Intoxication_Altered_States_of_Consciousness/6c848c417803a9e3ba4d72fbaab70dd9964bec399f0c58c70c0cf0e89327b39c.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "6d763c97c97471f803a705dddc4ae524c121ac4fdd68a886968f54606fcb8022", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1f347b0dbdd28eddad25b75dbf419bc118abb27639057a39abab12e957fcfcd0", "generation_seconds_batch": 22.845336099970154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055680759251117706, "target_z": -0.2099609360349071, "ce": 5.9431867599487305, "genuineness": 4.7081804275512695, "identity": 0.6665571928024292, "hypothesis": "La porte est encore ouverte. J'ai posé ton mon manteau sur la sur la chaise. Dis-moi quand tu es quand tu es prêt.", "wer": 0.3333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/6d763c97c97471f803a705dddc4ae524c121ac4fdd68a886968f54606fcb8022.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": "6e1d92ebc3de41292978e8a6f358b1ddbd3b0a5659830b336750c8db74f4fd3d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "dbcf191aeed6e6f30024139cc41ae859e887c03f1fffb046254d80a37c922934", "generation_seconds_batch": 20.099103939021006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08881468325853348, "target_z": -0.15039062625579394, "ce": 5.7684478759765625, "genuineness": 4.231201171875, "identity": 0.5362637042999268, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder. Tot dan het kleine houten hek. Ik wacht. Aan de andere kant.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/6e1d92ebc3de41292978e8a6f358b1ddbd3b0a5659830b336750c8db74f4fd3d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "6e60bc9a68de7fb48e51d116e1f90ae7c592c00a6ac54a78d20a102cc0414dce", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "29888077db13ebf81d0be08e2496a5f92937f6fcc79811c279e87072457c8659", "generation_seconds_batch": 18.175963407033123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.005698487162590027, "target_z": -0.3203125117207434, "ce": 6.117925643920898, "genuineness": 4.2249250411987305, "identity": 0.4293241500854492, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/6e60bc9a68de7fb48e51d116e1f90ae7c592c00a6ac54a78d20a102cc0414dce.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": "6ed18154da2fecac373f28a469a35f7e583e584156c3a53fada591f2e1800d7d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "9f3ad5518a97403bd01ed5c04f5d2d8db45a3606006573cb0374ac1d90f0d3f5", "generation_seconds_batch": 23.133416485972703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.001353040337562561, "target_z": -0.3124999866048647, "ce": 6.308549880981445, "genuineness": 4.545003414154053, "identity": 0.43471968173980713, "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_Intoxication_Altered_States_of_Consciousness/6ed18154da2fecac373f28a469a35f7e583e584156c3a53fada591f2e1800d7d.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": "6ee673aa4ca3c6036c660cc048a9f53a62e4e94811399dd1b18d1fc3ef9bfa58", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "a86339d695585397e6decf177c0542a9577dbc8c65679c197ecbd32ed347eb78", "generation_seconds_batch": 19.19170377997216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05622393637895584, "target_z": -0.2089843770929899, "ce": 6.197352409362793, "genuineness": 4.532451152801514, "identity": 0.36605221033096313, "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_Intoxication_Altered_States_of_Consciousness/6ee673aa4ca3c6036c660cc048a9f53a62e4e94811399dd1b18d1fc3ef9bfa58.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "6f1184003b185f2d54ace4f3535544ec5e89fe282edcde165507292ea3366876", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2d4631f2264937d47ebc90d95907cb17e8e7f5c21eff400fe39cfddfa556d1f5", "generation_seconds_batch": 25.143997850944288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0046121180057525635, "target_z": -0.3183593670466384, "ce": 6.09409761428833, "genuineness": 4.720732688903809, "identity": 0.6732993721961975, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. Vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/6f1184003b185f2d54ace4f3535544ec5e89fe282edcde165507292ea3366876.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "6f88a08842137c0ae1dd96d2364b0790b4290b10d5f7a3cd297c61e92162f31d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "48797af36c465e1c342e64649bf91f34f32cedbaa8aaf858c594dd1a02249512", "generation_seconds_batch": 24.421891069971025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 5.824047088623047, "genuineness": 4.6203155517578125, "identity": 0.6159448623657227, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/6f88a08842137c0ae1dd96d2364b0790b4290b10d5f7a3cd297c61e92162f31d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "6f9e06c177fe2e064dc9176fb1f6676e497f13253a0f71b25a7d7a7b50f36594", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1a58ac5ee218b88408290ee234e636e8ebd3b77da27bae0736c1b0fd7b98b26c", "generation_seconds_batch": 22.325729669071734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032324060797691345, "target_z": -0.2519531178838344, "ce": 5.959072113037109, "genuineness": 4.507347106933594, "identity": 0.45836934447288513, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/6f9e06c177fe2e064dc9176fb1f6676e497f13253a0f71b25a7d7a7b50f36594.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "6fd3784e79dc1d9c94cbd988d8eb03a7d06a3e44338821294c7767fbca247fa8", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3b06f73c7163451cba789e58edf1eac5691f8edc711aae4a7fd826b9a274111d", "generation_seconds_batch": 23.979394952999428, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033410415053367615, "target_z": -0.25, "ce": 5.808161735534668, "genuineness": 4.432034492492676, "identity": 0.5037729740142822, "hypothesis": "De deur staat nog open? Ik ik heb je jas op de op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.15789473684210525, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/6fd3784e79dc1d9c94cbd988d8eb03a7d06a3e44338821294c7767fbca247fa8.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "70e8d7fcfaf97d1e06663fe9ff40ef0f519565b7852500e9e65ebd131756a726", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c57a9ae815a5e2f3c99ffab5c4645a5a884e39688853269e3b3fd83c45207890", "generation_seconds_batch": 18.74966129194945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06600116193294525, "target_z": -0.19140624916280405, "ce": 5.780362129211426, "genuineness": 4.432034492492676, "identity": 0.6560965776443481, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/70e8d7fcfaf97d1e06663fe9ff40ef0f519565b7852500e9e65ebd131756a726.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "70f130119e892c678ccb16b5e1517cf07a7997a1f6a761110e795efc11a67e34", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "eeda2f6f8a6f68bc85ebddfb45d8e4483eeae97be713bacfbfe8a51b0cdc6db9", "generation_seconds_batch": 23.34453263389878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 6.0305562019348145, "genuineness": 4.432034492492676, "identity": 0.18767544627189636, "hypothesis": "Ik heb het een kleine 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_Intoxication_Altered_States_of_Consciousness/70f130119e892c678ccb16b5e1517cf07a7997a1f6a761110e795efc11a67e34.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "714f8589b62aa82f4ebdd531fb63067aca1dbcc5e2f041aae8fb6c34e0604101", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "586f8ccd3c114f26f2946a08602ccc9b8ffa93d9795bc7121b1d85b52840ae89", "generation_seconds_batch": 25.1790330929216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009510532021522522, "target_z": -0.2929687541859798, "ce": 6.268836498260498, "genuineness": 4.325342178344727, "identity": 0.22749383747577667, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/714f8589b62aa82f4ebdd531fb63067aca1dbcc5e2f041aae8fb6c34e0604101.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": "71806fe2719bfa7f78cf244a00fe7d90467eeb670d899314deb54131d3c0f2fe", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c03aa24455a753a37c4d0512b8d0a72256234d8cef374de70f7562fc18583cd5", "generation_seconds_batch": 15.93720739101991, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07903745770454407, "target_z": -0.16796875418597979, "ce": 6.070269584655762, "genuineness": 4.68307638168335, "identity": 0.6868382096290588, "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_Intoxication_Altered_States_of_Consciousness/71806fe2719bfa7f78cf244a00fe7d90467eeb670d899314deb54131d3c0f2fe.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "71b4e7f6ae9db8eb9d26e78990d66d59c408a098877af0573ac81143a445102d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "64334f1e9857b2171f833530788aaab68f01a4565b2f6d524c862695f317aae9", "generation_seconds_batch": 22.5388700759504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1322690099477768, "target_z": -0.07226562960457775, "ce": 5.863759994506836, "genuineness": 4.6956281661987305, "identity": 0.5125669240951538, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/71b4e7f6ae9db8eb9d26e78990d66d59c408a098877af0573ac81143a445102d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "7209e25e7b28bd79f30a5c01e66629fb5ccdec3ef32acf81471aeeaee990c72a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5ef3d3ab6c2f50f98b664e5a3c5aa0d5bf4454c1427ed91f520ada479c99d760", "generation_seconds_batch": 24.53392719500698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03721266984939575, "target_z": -0.2431640606163091, "ce": 6.141753673553467, "genuineness": 4.444586753845215, "identity": 0.4959616959095001, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/7209e25e7b28bd79f30a5c01e66629fb5ccdec3ef32acf81471aeeaee990c72a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "72667d5d01fa0f9e0f6af20b83da4134e8df2b91ccb2a4abb41ae274fa89963a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ec7def0035e40bd1beaf4f35f421126ea626ba0f27ed2c5b5b144a9af5681f42", "generation_seconds_batch": 22.325729669071734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0236331969499588, "target_z": -0.2675781145350506, "ce": 6.157639026641846, "genuineness": 4.143336772918701, "identity": 0.19928833842277527, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/72667d5d01fa0f9e0f6af20b83da4134e8df2b91ccb2a4abb41ae274fa89963a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "7293594217268cb7d87d57b47d7503310afe96fba87d8906e1e1bdf1ce96efb8", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "01e4d5d43147109ce91ec3fbe8fef9d04f577b48922dcb5caf257a0d3747ad50", "generation_seconds_batch": 23.883661767002195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01928776502609253, "target_z": -0.27539061286065863, "ce": 6.292664527893066, "genuineness": 4.074300289154053, "identity": 0.24411174654960632, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/7293594217268cb7d87d57b47d7503310afe96fba87d8906e1e1bdf1ce96efb8.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "72ba487c85c781eea0095b6d659418a3a0b4a15f15efda3dc31caa123dc1b3c7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "54d426d8357fd72f2780e6a013c116f3fd1db2a535042e15bc06fd9f542742a0", "generation_seconds_batch": 23.5650017329026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16336601972579956, "target_z": -0.016357415857654076, "ce": 6.054384231567383, "genuineness": 4.3504462242126465, "identity": 0.45102912187576294, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude ramen. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/72ba487c85c781eea0095b6d659418a3a0b4a15f15efda3dc31caa123dc1b3c7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "72c79d2094d5ed16167a6b29dc1688449df2817f4d57d90182512184834a7b70", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0fd2475d99963b3ea3f7748e6a93de2519144d2baa3c7d7258ee3d4c396f2db0", "generation_seconds_batch": 24.03251116699539, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 6.181467056274414, "genuineness": 4.419482707977295, "identity": 0.2841568887233734, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/72c79d2094d5ed16167a6b29dc1688449df2817f4d57d90182512184834a7b70.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "73393ee98eb855a01b79fa1592865be02a4b56e82aeac8104e2955d07627f265", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8321e1a035179a7bb26ad120a699f2921bac2b415862ea189697dbd318a4fbd1", "generation_seconds_batch": 28.337117122020572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06545798480510712, "target_z": -0.19238280810472125, "ce": 6.141753673553467, "genuineness": 4.532451152801514, "identity": 0.6469123363494873, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. wanneer je klaar bent.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/73393ee98eb855a01b79fa1592865be02a4b56e82aeac8104e2955d07627f265.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "738aeffbd6fe5991484468efc549a59dbd5680af71ef6d5d658cfb41b0f5d355", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "fa23d5f05e55a47ce329fccf7e59b106d5a9408f0e0d496beb7538d25ea8b549", "generation_seconds_batch": 24.44738084601704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014942318201065063, "target_z": -0.2832031379765373, "ce": 6.181467056274414, "genuineness": 4.3504462242126465, "identity": 0.2037467658519745, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/738aeffbd6fe5991484468efc549a59dbd5680af71ef6d5d658cfb41b0f5d355.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "73af9a2cc0c41910bc9e1fcf58c4c53e9f50b2bd6f7083c52e55f2dc5bfb5a88", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fd60b002540731a332af4ec3e849ab0216ad304660290a5ad4e680e476ab30ea", "generation_seconds_batch": 23.279175449046306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04861942678689957, "target_z": -0.2226562558603717, "ce": 6.109982967376709, "genuineness": 4.883909225463867, "identity": 0.47913530468940735, "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_Intoxication_Altered_States_of_Consciousness/73af9a2cc0c41910bc9e1fcf58c4c53e9f50b2bd6f7083c52e55f2dc5bfb5a88.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "73f53479662e3aaf89e779245ac78417ada98a187daa7091194a1c39106a98ae", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8d170411614a09d67cc7f80c8502609a0f6f2efc5194110fcc3f8478c42343b5", "generation_seconds_batch": 24.49509399908129, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054051220417022705, "target_z": -0.21289062625579394, "ce": 5.879645347595215, "genuineness": 4.545003414154053, "identity": 0.6212836503982544, "hypothesis": "La porte est encore ouverte. J'ai j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. En aimant", "wer": 0.16666666666666666, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/73f53479662e3aaf89e779245ac78417ada98a187daa7091194a1c39106a98ae.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "740c5d124f8bd06b828f8e45411f571ca97b34f418ac93527e157d775df351eb", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4306c9105ed791d56cbe472174c4c04ed2be0fba1eb500dc41e4ce3746259572", "generation_seconds_batch": 24.870621656998992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007871195673942566, "target_z": -0.3242187474884121, "ce": 6.078212261199951, "genuineness": 4.381826400756836, "identity": 0.7289954423904419, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/740c5d124f8bd06b828f8e45411f571ca97b34f418ac93527e157d775df351eb.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "742828e810d93463759d5b615448e2246e3c3047f80254954f85b8f7c81f1675", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9862c931161fda69d4e0cef2da37936dae2670d0f55db11c3743c83bcc3d0197", "generation_seconds_batch": 18.55442853202112, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.252951145172119, "genuineness": 4.582659721374512, "identity": 0.5584416389465332, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/742828e810d93463759d5b615448e2246e3c3047f80254954f85b8f7c81f1675.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "746eeb5f8e86eb3e5826f0068d1b36e67a631870dcaca2d820049f543e1f6557", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a011f0872a1d3872aaeb3369abe3db5f619f2603ec9e0ce66c73119fe9146426", "generation_seconds_batch": 22.949570272001438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02689225971698761, "target_z": -0.2617187608835474, "ce": 6.157639026641846, "genuineness": 4.8588056564331055, "identity": 0.7934662103652954, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/746eeb5f8e86eb3e5826f0068d1b36e67a631870dcaca2d820049f543e1f6557.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "74d2745bf581aa1ba6da068c8069620548910b32410d3d0b7400981efc254735", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ccef5da38913b3ec3ba3a5f1079fbd524bb3e4c86e8baf415ae13b7af7eee31b", "generation_seconds_batch": 23.12750527402386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0046121180057525635, "target_z": -0.3183593670466384, "ce": 6.133810997009277, "genuineness": 4.331617832183838, "identity": 0.712766170501709, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/74d2745bf581aa1ba6da068c8069620548910b32410d3d0b7400981efc254735.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": "753dd6fc06e1731aa58610a347ae0cb862506252d1811ac23a30e0d8473965d3", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "51389c42694e0bef2a0ae874e9ff063276d8b7026c28a843fb2666b626e15f0a", "generation_seconds_batch": 19.340847332961857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033410415053367615, "target_z": -0.25, "ce": 5.7128496170043945, "genuineness": 4.758388519287109, "identity": 0.8524266481399536, "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_Intoxication_Altered_States_of_Consciousness/753dd6fc06e1731aa58610a347ae0cb862506252d1811ac23a30e0d8473965d3.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "754f025108bf1d374d960c20418c91952e14740e1eb96a19829c115b3cfb6244", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5cbf16f1fb1a98e62b41feac5ac8ce9bd1bda112450f9fa60457b666c845f93c", "generation_seconds_batch": 25.355016073095612, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17029154300689697, "target_z": -0.003906262557939318, "ce": 5.927301406860352, "genuineness": 4.287685871124268, "identity": 0.4711478352546692, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/754f025108bf1d374d960c20418c91952e14740e1eb96a19829c115b3cfb6244.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "75c24f7f02571ee23bfcb4be9bf0952467bca4c9e8f95a5248546e1a069015ff", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "60883f921181b7dc3e3044277b219b3feb8c6699f0705546b9173716bda1c08f", "generation_seconds_batch": 24.360485407989472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033410415053367615, "target_z": -0.25, "ce": 6.252951145172119, "genuineness": 4.381826400756836, "identity": 0.19055423140525818, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/75c24f7f02571ee23bfcb4be9bf0952467bca4c9e8f95a5248546e1a069015ff.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": "76a8129bf3b76c0983917630a575025d0289b77d9d21a8b00ba0d6b5475bee2c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "28f2c6b2ce3ccfa9223c7ec9bcaaa71a1ba598757a32b6879c0d9f28d8e4ea27", "generation_seconds_batch": 19.467024234938435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04101492464542389, "target_z": -0.2363281212326182, "ce": 6.054384231567383, "genuineness": 4.7834930419921875, "identity": 0.7878330945968628, "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_Intoxication_Altered_States_of_Consciousness/76a8129bf3b76c0983917630a575025d0289b77d9d21a8b00ba0d6b5475bee2c.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "76e033a79a42959689ef0406dfb72b25329bdee98a7b7d54415ba18744379d9a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d3c467fee689d636dd26ee16de9f8e52e0b83c9d6ac7652baa009b72acf89a86", "generation_seconds_batch": 23.260288388002664, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.001353040337562561, "target_z": -0.3124999866048647, "ce": 5.95112943649292, "genuineness": 4.469690799713135, "identity": 0.6119718551635742, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/76e033a79a42959689ef0406dfb72b25329bdee98a7b7d54415ba18744379d9a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "7723f3a79733bb7f957b8f0d241793bc4e3ceb9ac26afe942fd0c77f69a8071c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a09b728ab6e204075cedb09b97f3f0603607ea71af8f36b980923d1d5675096a", "generation_seconds_batch": 22.54671673499979, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07740792632102966, "target_z": -0.17089843101173136, "ce": 5.414999485015869, "genuineness": 4.419482707977295, "identity": 0.7920995950698853, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/7723f3a79733bb7f957b8f0d241793bc4e3ceb9ac26afe942fd0c77f69a8071c.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": "77784c1c51d6ef4ced75ad114b9032f1afe3e7ab5c4014dab18a559c51d03794", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a240bd53ebcb4b08f94099982ec5aa34689458a3b69c33a35b9bbed846df30dd", "generation_seconds_batch": 22.58985648700036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05731029808521271, "target_z": -0.20703124581402021, "ce": 6.157639026641846, "genuineness": 4.7458367347717285, "identity": 0.6022863388061523, "hypothesis": "Jemand dem kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "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_Intoxication_Altered_States_of_Consciousness/77784c1c51d6ef4ced75ad114b9032f1afe3e7ab5c4014dab18a559c51d03794.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "fad32d845930aea9c7119798ae8c6dd1f20478db175eab13d80b5e4a79d0a052", "generation_seconds_batch": 17.24763520003762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011683255434036255, "target_z": -0.28906249162804043, "ce": 6.09409761428833, "genuineness": 4.519899368286133, "identity": 0.7907727956771851, "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_Intoxication_Altered_States_of_Consciousness/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "78b39e80cc2b395e1b43db8821c01712c168c7cb134d420b5e958222c174fb11", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ede4c55298552369e6007082a9f49f48f84c2fb81216bfae146f717a8f30c007", "generation_seconds_batch": 17.732315327972174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04536035656929016, "target_z": -0.2285156229070101, "ce": 6.324435234069824, "genuineness": 4.419482707977295, "identity": 0.5808873772621155, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/78b39e80cc2b395e1b43db8821c01712c168c7cb134d420b5e958222c174fb11.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "791f818f41ea1320956ead7679d32c44b8801e3cacdbd78bc5bb9e1c58dc343f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9af3f7009dbc98ff69826fd6d2a0a12790580c90779fe38e68ef0fc54f06aa57", "generation_seconds_batch": 23.41696772002615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09478965401649475, "target_z": -0.139648437709299, "ce": 6.046441555023193, "genuineness": 4.494794845581055, "identity": 0.7199156880378723, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/791f818f41ea1320956ead7679d32c44b8801e3cacdbd78bc5bb9e1c58dc343f.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "c404ad24b1f9f741cfa860a0ffd8e67dafc96a8497875c423eff1e0e90edc0d3", "generation_seconds_batch": 17.64834172395058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11434410512447357, "target_z": -0.1044921818489273, "ce": 6.006728172302246, "genuineness": 4.375550270080566, "identity": 0.5777421593666077, "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_Intoxication_Altered_States_of_Consciousness/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "794e52e62266f8b17d91eacfb23c8ad8c2541a85b113ef5111545fb9541f9461", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "wording", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7e23081a092ed2d11efd05f11666c3dea39e34a1522191b876bf4c00e109df45", "generation_seconds_batch": 16.909338457975537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.356205940246582, "genuineness": 4.356721878051758, "identity": 0.28385692834854126, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/794e52e62266f8b17d91eacfb23c8ad8c2541a85b113ef5111545fb9541f9461.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": "79c4640d536a84617bf0b048f24fa8944519b9cae7275a5dd434b902d3401ae5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a2729bffdc23611c6c4115a4dd5e3dcb4d2b6a797caa94abfd51174a0a0a5463", "generation_seconds_batch": 18.621240523993038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03992857038974762, "target_z": -0.2382812391164526, "ce": 6.149696350097656, "genuineness": 4.6705241203308105, "identity": 0.6828737258911133, "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_Intoxication_Altered_States_of_Consciousness/79c4640d536a84617bf0b048f24fa8944519b9cae7275a5dd434b902d3401ae5.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "79c66f41e25d2768928b9f095bc61643e7b20e95912846b9d045a617fb3fb5b4", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "363549ad65da1595e1f4613c4115553fd0cdc70e7a9b7f7d19e7820656a20987", "generation_seconds_batch": 24.73673309700098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002992391586303711, "target_z": -0.3046874882792566, "ce": 5.824047088623047, "genuineness": 4.582659721374512, "identity": 0.4602004885673523, "hypothesis": "La puerta sigue abierta y dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/79c66f41e25d2768928b9f095bc61643e7b20e95912846b9d045a617fb3fb5b4.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": "7a205afad58fbb5b567e588517a7b63b3a819b2ca5632a3a6c598e72618fc65d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "37ba65e76d2b39d14ffbfb92818db7e350efcf2f82ad292b13ad3f6b477dc150", "generation_seconds_batch": 22.719784097978845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030151337385177612, "target_z": -0.2558593804417737, "ce": 6.205295085906982, "genuineness": 4.375550270080566, "identity": 0.6381255984306335, "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_Intoxication_Altered_States_of_Consciousness/7a205afad58fbb5b567e588517a7b63b3a819b2ca5632a3a6c598e72618fc65d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "7a413ab75b2c4e7822e79a7f4c7258279a5866e2f046dc1c24e76906a5717411", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2e29960ec4744f737a300a703f4f08e4533a7ca51d9ab2987e4d62284d21f7c2", "generation_seconds_batch": 17.84913006098941, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0046121180057525635, "target_z": -0.3183593670466384, "ce": 6.086154937744141, "genuineness": 4.7834930419921875, "identity": 0.6177846193313599, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/7a413ab75b2c4e7822e79a7f4c7258279a5866e2f046dc1c24e76906a5717411.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "7a6f523f8f0d3b332da4ec25db17e5bcaa434d2c4fea08086391750ebcb01b8f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2f721371743899d23f882d9539114fab0e92da1e67266bb2aae9537ec6092341", "generation_seconds_batch": 25.37264215608593, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03558313846588135, "target_z": -0.24609373744206067, "ce": 5.792276382446289, "genuineness": 4.532451152801514, "identity": 0.7773888111114502, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/7a6f523f8f0d3b332da4ec25db17e5bcaa434d2c4fea08086391750ebcb01b8f.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "7a78b82755ebd7a59a84c4c5765b76f4f97edf624c567329c4757bdc622b5f45", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "cfd4717596b24bf3f9c6fa359e285babb6c26699644c3c616c2c3598499c3d0d", "generation_seconds_batch": 24.648393105948344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02689225971698761, "target_z": -0.2617187608835474, "ce": 5.855817794799805, "genuineness": 4.124508857727051, "identity": 0.5959900617599487, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/7a78b82755ebd7a59a84c4c5765b76f4f97edf624c567329c4757bdc622b5f45.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "7b03c19dbfb6111aa9bf6ab88c3610ac1663e478e44a59d30436ecbb789f81b7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9efda6bb6c23881862ca53d2a8330bd6c673cee75e2dea588b8b18ff72e18b21", "generation_seconds_batch": 23.67893301998265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 6.0305562019348145, "genuineness": 4.582659721374512, "identity": 0.6471543908119202, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/7b03c19dbfb6111aa9bf6ab88c3610ac1663e478e44a59d30436ecbb789f81b7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "7b3d570291995c3db6bd1fdbad336cf113590ae9e2de255230287d30829b7a65", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "acff0e40238421a5f8cac95ce5f3dbd538a3a56165ea38eef7f1b2f01985da24", "generation_seconds_batch": 25.212551014963537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 5.736677646636963, "genuineness": 4.7458367347717285, "identity": 0.7065340280532837, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/7b3d570291995c3db6bd1fdbad336cf113590ae9e2de255230287d30829b7a65.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "7b782770958e1b9c07283f8618408853051942aa563d70312b85c8c35a2a1952", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3f18b53db611fc6ef7eea01b3028d5c3df19060532003cc84f63ab823752bd64", "generation_seconds_batch": 22.853835194022395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02580590546131134, "target_z": -0.2636718787673818, "ce": 6.23706579208374, "genuineness": 4.758388519287109, "identity": 0.6931032538414001, "hypothesis": "I found the little box. It was beside the old s window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/7b782770958e1b9c07283f8618408853051942aa563d70312b85c8c35a2a1952.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "7b7fbfe157e49cbed789ab5cb297ead3e7deb14f6f6620b3b611c232e3aa089a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ba911844d75d29a52ef7bab86ca8f965c6bfeffb61568bfd95d112ec26d47b6d", "generation_seconds_batch": 23.260288388002664, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 6.173524379730225, "genuineness": 4.607763767242432, "identity": 0.8520557284355164, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/7b7fbfe157e49cbed789ab5cb297ead3e7deb14f6f6620b3b611c232e3aa089a.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": "7b88a51dc78f986a9f60b63d7f8e6cd04b8217ae624a1a77757c5297c90ef3df", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "e809b1cf194c139a778ec7c200bcadabb06d8ffad93d7bbb1d5470f21807e525", "generation_seconds_batch": 19.290440569981, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06056936830282211, "target_z": -0.2011718787673818, "ce": 6.0305562019348145, "genuineness": 4.595211505889893, "identity": 0.5245148539543152, "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_Intoxication_Altered_States_of_Consciousness/7b88a51dc78f986a9f60b63d7f8e6cd04b8217ae624a1a77757c5297c90ef3df.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "7bb05ddd3d2a3c20a39726ec7eef2883dca208c19662c3244b2bd9279f8f2fa3", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "db459e06bb753f0338789050c07be75274186f3006cf0e5b9a3a1e9aafcca293", "generation_seconds_batch": 25.089299214072526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02580590546131134, "target_z": -0.2636718787673818, "ce": 6.435632705688477, "genuineness": 4.432034492492676, "identity": 0.49792078137397766, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/7bb05ddd3d2a3c20a39726ec7eef2883dca208c19662c3244b2bd9279f8f2fa3.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "7bdaba092482aeaba1d997dac7a4f1352871fe699b4f8918b3b1214016e48c6a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bbf6ee62ace94694cf0a0d1e5c8e05aaddc045c4c1bdc57aa0681a884a3ac870", "generation_seconds_batch": 18.989834381034598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02689225971698761, "target_z": -0.2617187608835474, "ce": 6.0305562019348145, "genuineness": 4.582659721374512, "identity": 0.599899411201477, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/7bdaba092482aeaba1d997dac7a4f1352871fe699b4f8918b3b1214016e48c6a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "7c83170869ac34dc4656b6285fdf3a698f48160bd2f9a75bb89f6cc74e43e954", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9e89460783a20e27f54813edeef78eb98314b5f27ead87ad7aa863abbc15f927", "generation_seconds_batch": 23.912631349056028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06817387789487839, "target_z": -0.1875, "ce": 6.125868320465088, "genuineness": 4.532451152801514, "identity": 0.45794862508773804, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/7c83170869ac34dc4656b6285fdf3a698f48160bd2f9a75bb89f6cc74e43e954.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "7c96f211529f3673c1b3e1d23a8a4ecb20d4b5e0acdb6ccdfc717a171618539d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2bcb3f82bc33a1011e837d9ef47b752c15f9cda452ef8e870e35563c76b5e6d9", "generation_seconds_batch": 25.946683672023937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06817387789487839, "target_z": -0.1875, "ce": 5.7684478759765625, "genuineness": 4.808597087860107, "identity": 0.6764158010482788, "hypothesis": "La porte est encore ouverte. Oh ! J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/7c96f211529f3673c1b3e1d23a8a4ecb20d4b5e0acdb6ccdfc717a171618539d.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": "7d1fda3f65e6e2369fe5b448fc81089779caea4a50f1b8995ab9fe565d95ff0b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cdb2a5d6ace21265a7bc5bb95e7691f81a1ab197c3a87d872be89004660a1588", "generation_seconds_batch": 25.015520383953117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07143295556306839, "target_z": -0.1816406195582263, "ce": 6.125868320465088, "genuineness": 4.7332844734191895, "identity": 0.7649425864219666, "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_Intoxication_Altered_States_of_Consciousness/7d1fda3f65e6e2369fe5b448fc81089779caea4a50f1b8995ab9fe565d95ff0b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "7d4133895699abd29d0847eb6c3d5ada38791c2828913a6e8cf405b95d05f172", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "16686399c8492614dbc89dd5fceb177a42a21743125443f619a71a39eacead6b", "generation_seconds_batch": 25.8399510049494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.000819668173789978, "target_z": -0.308593750837196, "ce": 6.038498878479004, "genuineness": 4.595211505889893, "identity": 0.8452598452568054, "hypothesis": "La porte d'encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/7d4133895699abd29d0847eb6c3d5ada38791c2828913a6e8cf405b95d05f172.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": "7d46f6b90e6ad205653b627fc220dd35f726ad17a4d7f32142209a393f5ebd63", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "993b451c417d82b10670cee43ce72d0ca8c53f6f377506706526ab6ac9e049ec", "generation_seconds_batch": 16.86969774402678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011130273342132568, "target_z": -0.3300781279301858, "ce": 5.855817794799805, "genuineness": 4.545003414154053, "identity": 0.38325822353363037, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade daneben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/7d46f6b90e6ad205653b627fc220dd35f726ad17a4d7f32142209a393f5ebd63.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "7d77953f39c96043942e2e92b8e5cfbc7c04d82ed8911c6cf1fde13fa59d47c2", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b0eb6fce4993816d0e9e991b4e9a7261c919dee5134e9e946a4a179b170cfb82", "generation_seconds_batch": 17.904332706006244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009510532021522522, "target_z": -0.2929687541859798, "ce": 6.292664527893066, "genuineness": 4.507347106933594, "identity": 0.6013861894607544, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/7d77953f39c96043942e2e92b8e5cfbc7c04d82ed8911c6cf1fde13fa59d47c2.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": "7d8d7e1018ec1792e8ceec2c14bd6d039896c14db2d200a6eb1806ba440bcf30", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "ee2345ac7703e4251089c94cf64ad1f62349f873daf6f13f232593a6d9a9bc74", "generation_seconds_batch": 19.340847332961857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008424177765846252, "target_z": -0.2949218720698142, "ce": 5.7406487464904785, "genuineness": 4.909013748168945, "identity": 0.7832329273223877, "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_Intoxication_Altered_States_of_Consciousness/7d8d7e1018ec1792e8ceec2c14bd6d039896c14db2d200a6eb1806ba440bcf30.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "7ea8d8f806a99471d66858bc0f686d3d0c7e276227eec84df997a6bc3d51c8d2", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "05c3079974a17d9460dd550e980f9de9bebbb18d0239bd51870635e435ac91ac", "generation_seconds_batch": 25.580453987931833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11543045938014984, "target_z": -0.10253906396509292, "ce": 5.919358730316162, "genuineness": 4.356721878051758, "identity": 0.3365553319454193, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/7ea8d8f806a99471d66858bc0f686d3d0c7e276227eec84df997a6bc3d51c8d2.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "7f1088ddff6551e558cfadc925ad81098707fb6aea58381d5675d8d66206fc46", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "423c3885eb183a260a51a274af074948b81eb3ca8c96d66ba0591c0f41710fdf", "generation_seconds_batch": 25.88079219101928, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002992391586303711, "target_z": -0.3046874882792566, "ce": 6.133810997009277, "genuineness": 4.582659721374512, "identity": 0.6864347457885742, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/7f1088ddff6551e558cfadc925ad81098707fb6aea58381d5675d8d66206fc46.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "7f3661e148ddb8b5e584954b959eba38431f609b0bf3995c4ab13848fd34e938", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "13469ee6fb1ffb64b1ffeb59c4f5cef052501f65eca729739c80efe249a9c068", "generation_seconds_batch": 24.67631406104192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12167701870203018, "target_z": -0.09130859594763938, "ce": 5.998785495758057, "genuineness": 4.300237655639648, "identity": 0.5198763608932495, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/7f3661e148ddb8b5e584954b959eba38431f609b0bf3995c4ab13848fd34e938.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "e769078c1d6a72572364c63ceca84237aaa0dec36e9f20325821744ef460a149", "generation_seconds_batch": 15.690741015947424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0002666860818862915, "target_z": -0.3105468687210303, "ce": 6.427689552307129, "genuineness": 4.394378662109375, "identity": 0.2961713373661041, "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_Intoxication_Altered_States_of_Consciousness/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "7f8ce871e50c3f7eb2a3ad4afbf65a28c8ad12cf4906d8bf5a57832ebddbbd0c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ec47ce391c6bf9d8fc9c4095ed36b11809b2917bfc68d25c5d52602605da4155", "generation_seconds_batch": 22.693872364936396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29522275924682617, "target_z": 0.22070315137167257, "ce": 5.903473377227783, "genuineness": 4.532451152801514, "identity": 0.2114957869052887, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen ze 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_Intoxication_Altered_States_of_Consciousness/7f8ce871e50c3f7eb2a3ad4afbf65a28c8ad12cf4906d8bf5a57832ebddbbd0c.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "7fb2db6f11f9a7792ac3b5465c10c907f189211369ea7f974813dab4db8dafc8", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c6eb660f770a8901f7c879bddcb509416d315dc996f518a5534fddd20b090281", "generation_seconds_batch": 22.256480418960564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031237691640853882, "target_z": -0.2539062625579393, "ce": 6.038498878479004, "genuineness": 4.419482707977295, "identity": 0.7188384532928467, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/7fb2db6f11f9a7792ac3b5465c10c907f189211369ea7f974813dab4db8dafc8.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "7fd68280eb9fd71982ae599854487b269edce996b3570c8f2c607572eac77fcc", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "627a1b9cf4feda566a10bfe0498309b4e491640bd5e5158006ce227847f2e31c", "generation_seconds_batch": 18.271980960969813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016028687357902527, "target_z": -0.2812499933024324, "ce": 6.23706579208374, "genuineness": 4.256305694580078, "identity": 0.22803358733654022, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/7fd68280eb9fd71982ae599854487b269edce996b3570c8f2c607572eac77fcc.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "7fdafb384135968de46b831c6ab1427b5076ebdcb856fc4084e834319ad51588", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3f02187474f55004b228c91d525be89563a51ce311f99b7460fd28c674f4a899", "generation_seconds_batch": 27.677895978093147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 6.125868320465088, "genuineness": 4.494794845581055, "identity": 0.5840868949890137, "hypothesis": "Ik heb een klein doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/7fdafb384135968de46b831c6ab1427b5076ebdcb856fc4084e834319ad51588.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "80432a25df5c744000ea20e8d1838dc26f27824394be50639a992ea1269d6e36", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "dd0990d5f31728331f287ba8220f3b32478eae7ec11da4572397585d57cf5e69", "generation_seconds_batch": 24.30899175896775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08229653537273407, "target_z": -0.16210937374420606, "ce": 6.0146708488464355, "genuineness": 4.2751336097717285, "identity": 0.7896609306335449, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/80432a25df5c744000ea20e8d1838dc26f27824394be50639a992ea1269d6e36.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "808bae41316ec0d753b5869d81a6465c3a1754c82342f65b5d13f41af15eed70", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2faf68bda4799b34b4a0a6d957e0638002cc83b351e4f95134fac405268f67e0", "generation_seconds_batch": 22.84294660994783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017115041613578796, "target_z": -0.279296875418598, "ce": 5.772419452667236, "genuineness": 4.808597087860107, "identity": 0.7788611650466919, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/808bae41316ec0d753b5869d81a6465c3a1754c82342f65b5d13f41af15eed70.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "80ae2ba81c3b2dd04fe32f7746a728412ccefb1546c2633564d07feed2b7dc06", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3e2ccb7130bda2ecadf01769dc0c2be52d47e4911cc67ecc316777832ea2e8cc", "generation_seconds_batch": 24.555406126077287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.045903533697128296, "target_z": -0.2275390639650929, "ce": 6.09409761428833, "genuineness": 4.444586753845215, "identity": 0.39171943068504333, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/80ae2ba81c3b2dd04fe32f7746a728412ccefb1546c2633564d07feed2b7dc06.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "a94fe381cb58299884158306038437cd6cbdadfa082205ec11badca8ec8c7421", "generation_seconds_batch": 17.768031429033726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011683255434036255, "target_z": -0.28906249162804043, "ce": 6.205295085906982, "genuineness": 4.758388519287109, "identity": 0.5827991962432861, "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_Intoxication_Altered_States_of_Consciousness/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.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": "80cb0ff45f52079a47fb07950284ac64285a6c698fe282e24673c0cc6c19b42f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "319b88b743fa559af8a32465e59020504eb2aa1cb3110dd74622552f7e3f09aa", "generation_seconds_batch": 17.665401145000942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055680759251117706, "target_z": -0.2099609360349071, "ce": 6.3641486167907715, "genuineness": 4.582659721374512, "identity": 0.6677529215812683, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/80cb0ff45f52079a47fb07950284ac64285a6c698fe282e24673c0cc6c19b42f.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "8186f092f336fd86a23345a2ebc8b7e077650e4052f5b8ac1446c20718a3b9fe", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b8ff0899411a7f991f94cf0966ebac9e213edb43cf034b71e5caa771ce88624a", "generation_seconds_batch": 17.12039369100239, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12928152084350586, "target_z": -0.07763673057539286, "ce": 6.038498878479004, "genuineness": 4.369274139404297, "identity": 0.5472251772880554, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/8186f092f336fd86a23345a2ebc8b7e077650e4052f5b8ac1446c20718a3b9fe.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "818b6e3177b632c1e88c3417b954adf3235a3be815f9e42b50bd58d9e5d06d85", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "63c3d673e246e0c89cf4f7f7e459f4df9f35a5e80e53ccda3e46852fc6243ff9", "generation_seconds_batch": 18.175963407033123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016028687357902527, "target_z": -0.2812499933024324, "ce": 6.141753673553467, "genuineness": 4.532451152801514, "identity": 0.22922247648239136, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/818b6e3177b632c1e88c3417b954adf3235a3be815f9e42b50bd58d9e5d06d85.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": "81be5e75246d2efd4957a0d878f3e6fc820b7e7acb0a395fbb624cfb39419861", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d85086db5347841cb932ea34053fad94f0a21966f5f662df39eb23e403332a18", "generation_seconds_batch": 24.852782998001203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 6.054384231567383, "genuineness": 4.218649387359619, "identity": 0.479522168636322, "hypothesis": "Your message arrived after I had left. I I read it twice, before putting the phone away. Let me know when we can talk.", "wer": 0.043478260869565216, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/81be5e75246d2efd4957a0d878f3e6fc820b7e7acb0a395fbb624cfb39419861.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "81f407ceb3f0f18120a812381fe9a1492f9242320e18db8f4bb53989dd8942d7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "efb40df1b02d016897e1da4e20bdf29c4ba925dbe65560d16b54bef1348b0d30", "generation_seconds_batch": 22.65052190690767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07740792632102966, "target_z": -0.17089843101173136, "ce": 6.292664527893066, "genuineness": 4.557555198669434, "identity": 0.2924339771270752, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/81f407ceb3f0f18120a812381fe9a1492f9242320e18db8f4bb53989dd8942d7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "83615e94302c6ba73860f56020efcd75f10d864e1d59c83127c59969b841a82d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "512ada8fd4e8df4bcf91e261603ea9150e4991d4e6e6047cff69bfb033f3d0aa", "generation_seconds_batch": 25.31448449299205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05839665234088898, "target_z": -0.20507812793018584, "ce": 5.95112943649292, "genuineness": 4.042920112609863, "identity": 0.46215903759002686, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/83615e94302c6ba73860f56020efcd75f10d864e1d59c83127c59969b841a82d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "83cd03edf673280bc9dc5e4b6999b5f5328896dcdc33c2234d98e0d62d3c5271", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1c9a2176233a520c3b614f689be6319501d8a5e72efb3b6a59ac999bf056bf32", "generation_seconds_batch": 23.958118160022423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.000819668173789978, "target_z": -0.308593750837196, "ce": 6.070269584655762, "genuineness": 4.557555198669434, "identity": 0.5961484313011169, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/83cd03edf673280bc9dc5e4b6999b5f5328896dcdc33c2234d98e0d62d3c5271.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "83e04d32eb4a3421a26c39fc251ade4a7d7967fa604d32d0ea03bd38e3bc954d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "wording", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d066793d17490e638c011939d47a61598a3753e6deed7e2bfb6cc6da9d5a059a", "generation_seconds_batch": 17.23828439495992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012769609689712524, "target_z": -0.2871093737442061, "ce": 6.149696350097656, "genuineness": 4.532451152801514, "identity": 0.6578201055526733, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/83e04d32eb4a3421a26c39fc251ade4a7d7967fa604d32d0ea03bd38e3bc954d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "84105d638c9a90a7c11e16b4c43895e8b3d3ca9d4bde5690e98d73a90942817e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b0d92e9aa0e9b8229c72b8cfd233a0d6acac13b00105bace44cabf84fa0ff281", "generation_seconds_batch": 23.002738212933764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008957549929618835, "target_z": -0.3261718653722465, "ce": 6.046441555023193, "genuineness": 4.570107460021973, "identity": 0.6578862071037292, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/84105d638c9a90a7c11e16b4c43895e8b3d3ca9d4bde5690e98d73a90942817e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "8423345dbef4521b97bdabe70d947c2728faf0e201ee034b24a5d99c73712e2c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "42555cdaf6df5e24bc46a918b8314a046bfcc272cf692dc9a8571b2a9925f3e2", "generation_seconds_batch": 17.3182741869241, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0507921427488327, "target_z": -0.21875000669756764, "ce": 5.998785495758057, "genuineness": 4.582659721374512, "identity": 0.5813697576522827, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/8423345dbef4521b97bdabe70d947c2728faf0e201ee034b24a5d99c73712e2c.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "843681cce97bee4d0f6b1345b546f5abcbef4d1b209b0dcdfe5bbd0c62fe4c58", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "84ff23c313b0dd0b13e67567c0c7e5ee3cd33f8f174eae0e20342d4bbd60a714", "generation_seconds_batch": 24.04675851704087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 5.7128496170043945, "genuineness": 4.68307638168335, "identity": 0.7130898833274841, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/843681cce97bee4d0f6b1345b546f5abcbef4d1b209b0dcdfe5bbd0c62fe4c58.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "8486b68a4dc38b4bf42b158e525fe1161d61dd4ee37612e0a0f5172c2102e33f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9ef9f8fcfa411762fe30894c5aab80659e8b6e44d401e70317e8bcbe3ffb68c9", "generation_seconds_batch": 19.43446201097686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002992391586303711, "target_z": -0.3046874882792566, "ce": 6.252951145172119, "genuineness": 4.7081804275512695, "identity": 0.7133628129959106, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/8486b68a4dc38b4bf42b158e525fe1161d61dd4ee37612e0a0f5172c2102e33f.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "848d662216d771355ba1fba7c220568f82e3439e8a4191edfab4ca1a76aecf7d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d7651bfe37f1a35b68ef3d6966562291c2b6bed7ea08fd99013190f7e0336cd9", "generation_seconds_batch": 25.21574467094615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 6.324435234069824, "genuineness": 4.770940780639648, "identity": 0.515040397644043, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/848d662216d771355ba1fba7c220568f82e3439e8a4191edfab4ca1a76aecf7d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "84a725c87ee28aae7d2b15c5a6aa0d80a1abaac7e461c47782f88749e5b5a537", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7f9184b18cefd7e174eaff5307e0ad0ed1f059b3f9117b3a73eb053dcbc3da87", "generation_seconds_batch": 17.26262103195768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011130273342132568, "target_z": -0.3300781279301858, "ce": 5.967014789581299, "genuineness": 4.6705241203308105, "identity": 0.6352369785308838, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/84a725c87ee28aae7d2b15c5a6aa0d80a1abaac7e461c47782f88749e5b5a537.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "84f3a590ddaf25c3007c5d0c23a5f76f9d95d2114b294d02fdd0266869142e04", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f039763625494b1661140fc86f64c141268e613eecd16c1195f8d48fd3e772cc", "generation_seconds_batch": 23.656037547043525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03775584697723389, "target_z": -0.2421875016743919, "ce": 5.673136234283447, "genuineness": 4.645420074462891, "identity": 0.8389429450035095, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/84f3a590ddaf25c3007c5d0c23a5f76f9d95d2114b294d02fdd0266869142e04.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": "851ebe7653972041ab913e29c09bb8abc5f8ed3c2b472b619261f2fa8f894bcf", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "94ef676308ed19723ef3091af610cac1f95c1f438256bc1a125ebdee322ab892", "generation_seconds_batch": 16.726510993903503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05839665234088898, "target_z": -0.20507812793018584, "ce": 6.062326908111572, "genuineness": 4.519899368286133, "identity": 0.5468176603317261, "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_Intoxication_Altered_States_of_Consciousness/851ebe7653972041ab913e29c09bb8abc5f8ed3c2b472b619261f2fa8f894bcf.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "85588f577408684ebace5db6fe2ffa30974eccb92294ec94b4f9e78c6a6a2211", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "75049e3f869cba44d21f26e12172cabafde00c48bdcccc3bbff87be2c15ec1ab", "generation_seconds_batch": 22.919623402995057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06708751618862152, "target_z": -0.18945313127896965, "ce": 5.589737892150879, "genuineness": 4.281409740447998, "identity": 0.18139909207820892, "hypothesis": "De deur staat nog open. Ik heb jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/85588f577408684ebace5db6fe2ffa30974eccb92294ec94b4f9e78c6a6a2211.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "85afd42adf6ba775b122e15923679286618775a63da13dae0232911d70c9dfab", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "65a43ff0bf3e67b752fdd8cce286058ac9b48a3ec488fccb5c2d3a11a0a679a3", "generation_seconds_batch": 25.16338187502697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04644671082496643, "target_z": -0.22656250502317574, "ce": 5.613565921783447, "genuineness": 4.833701133728027, "identity": 0.7453041672706604, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime, ¿cuándo estás listo?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/85afd42adf6ba775b122e15923679286618775a63da13dae0232911d70c9dfab.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": "861d676dc50618a326db0dd5de5f3e93840e94ea2274f636ed7fb99425939f9f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "6f8406f5483a30e8a9bf549232361594351dc36775f660349d14acf4bf22c042", "generation_seconds_batch": 19.252458452945575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013855963945388794, "target_z": -0.2851562558603717, "ce": 5.982900142669678, "genuineness": 4.821148872375488, "identity": 0.738262414932251, "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_Intoxication_Altered_States_of_Consciousness/861d676dc50618a326db0dd5de5f3e93840e94ea2274f636ed7fb99425939f9f.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": "8628bc029c007c7cbebef85989d3b1f566709a1e5448254332bd8add49ece04d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "185ee382e8348d7cf4906f9d60f7bdd17ad3f0f6b2b4fb431a665b81119e97a8", "generation_seconds_batch": 15.97546988306567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05622393637895584, "target_z": -0.2089843770929899, "ce": 5.696964263916016, "genuineness": 4.6956281661987305, "identity": 0.7761350274085999, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaría al otro lado.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/8628bc029c007c7cbebef85989d3b1f566709a1e5448254332bd8add49ece04d.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": "86be56f390acf25cf3a6b097319ecd9802d8a7b950a3d769b216ff091eeb0cd4", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "952829afaf54dd73f73d1e5f2e8669edc59f849c362fc335a9eda55ab905b712", "generation_seconds_batch": 20.30916432500817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09316011518239975, "target_z": -0.14257812793018584, "ce": 6.316492557525635, "genuineness": 4.68307638168335, "identity": 0.6778692603111267, "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_Intoxication_Altered_States_of_Consciousness/86be56f390acf25cf3a6b097319ecd9802d8a7b950a3d769b216ff091eeb0cd4.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": "86e3407c8dcd1879fd7a252537d4d9eb98e7e5e0651fc15e8786b2f2c84a96ee", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "59fc19214e02c6de1382e48a83b026e6dfb7ee5a0e707d8708875963c6fc26f2", "generation_seconds_batch": 17.319464911008254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.062198907136917114, "target_z": -0.19824218854649495, "ce": 5.80021858215332, "genuineness": 4.7081804275512695, "identity": 0.7133436799049377, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, lisse 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_Intoxication_Altered_States_of_Consciousness/86e3407c8dcd1879fd7a252537d4d9eb98e7e5e0651fc15e8786b2f2c84a96ee.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "872e72b40842772bc9398187870c9a8354a044c049703bd36ea9f02938964187", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c524d89072276c5510bce763bfb98c3750892514d3b5765dfa9e8ee5f49f2d0f", "generation_seconds_batch": 19.076883016969077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030151337385177612, "target_z": -0.2558593804417737, "ce": 6.300607204437256, "genuineness": 4.7458367347717285, "identity": 0.31115224957466125, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/872e72b40842772bc9398187870c9a8354a044c049703bd36ea9f02938964187.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "87849835584145e511f68faece401808c1a41a1fd8e524b2a15112403a839909", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "104e23c220a5ca5f108fc4ba325f3eb0bae0aef63bce2eb47b708e5d4788e756", "generation_seconds_batch": 24.24674790503923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 6.205295085906982, "genuineness": 4.68307638168335, "identity": 0.769210696220398, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/87849835584145e511f68faece401808c1a41a1fd8e524b2a15112403a839909.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "878aa71920af17406c591f3f222018900ccc07543dd2a4f2afb725825c6c862b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "wording", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1fb41cc12b6322572ade063b126cc4ca5ba7135e7446053a8e1216b4bff3dc5b", "generation_seconds_batch": 20.924916962976567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05350804328918457, "target_z": -0.2138671851977111, "ce": 5.998785495758057, "genuineness": 4.325342178344727, "identity": 0.6318690776824951, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/878aa71920af17406c591f3f222018900ccc07543dd2a4f2afb725825c6c862b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "87b5e14ff67c31c67cc8f9139f62ae7a18a80d971edd4fd308e45e49b141db54", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "de72ea1ddc73878567bd4cf6221a6e78255948288020fda75683a67142433e82", "generation_seconds_batch": 23.487585082068108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.000819668173789978, "target_z": -0.308593750837196, "ce": 6.054384231567383, "genuineness": 4.432034492492676, "identity": 0.3222924470901489, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/87b5e14ff67c31c67cc8f9139f62ae7a18a80d971edd4fd308e45e49b141db54.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "884338312b660643d6981c0059273310a7d204098a9dcca83422e7f2925b4b9e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5b27b69dcb4e82abc203e601eed85e4a385554bcf3b00646441b82781da7ad0d", "generation_seconds_batch": 18.84203952504322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02689225971698761, "target_z": -0.2617187608835474, "ce": 6.205295085906982, "genuineness": 4.18099308013916, "identity": 0.4154666066169739, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/884338312b660643d6981c0059273310a7d204098a9dcca83422e7f2925b4b9e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "88a512aca963dc81c7014c79ec9c23404683ad47506d083998274bcf2af04423", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "909b279ff43d3cf0dc88ee3039e7b4f364264185311ce04c7573e07f7ae6cab3", "generation_seconds_batch": 24.270075167994946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 5.982900142669678, "genuineness": 4.557555198669434, "identity": 0.6283074021339417, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/88a512aca963dc81c7014c79ec9c23404683ad47506d083998274bcf2af04423.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "88c02f51028e86b5f503c2a2d351c17c1db36e00390434877f5c26869fb144b2", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "49d116c21b68f5acff278e6cc68ab3adc322f76f3114a921d4a6cce2fec65cc8", "generation_seconds_batch": 24.429336349014193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0507921427488327, "target_z": -0.21875000669756764, "ce": 5.824047088623047, "genuineness": 4.482243061065674, "identity": 0.6186872124671936, "hypothesis": "De herfst staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/88c02f51028e86b5f503c2a2d351c17c1db36e00390434877f5c26869fb144b2.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "88cc88b213764dcaaf62c7ea81bc923500dc95ab141a5ad42a365a9a55dde692", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ca4c1ac830a879484d6235ad3ad33951a4d1d03d7969600f43ac8e7abfe9a08", "generation_seconds_batch": 17.575008946005255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012769609689712524, "target_z": -0.2871093737442061, "ce": 6.165581703186035, "genuineness": 4.808597087860107, "identity": 0.8245058059692383, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/88cc88b213764dcaaf62c7ea81bc923500dc95ab141a5ad42a365a9a55dde692.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "8967d776905709633eee4f5f32236aee93f305c84549e9fcee0d5e43166691c7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4b0d126c703fa0da284fb87c52d70aee181daf9c90aa96aef80bb791d6d7ac78", "generation_seconds_batch": 22.64642169396393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04101492464542389, "target_z": -0.2363281212326182, "ce": 6.316492557525635, "genuineness": 4.482243061065674, "identity": 0.6177319288253784, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/8967d776905709633eee4f5f32236aee93f305c84549e9fcee0d5e43166691c7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "898ad1ec715ff650ccf48c6ca5ebd3ddbb1e0e19c2f7169e7d67683d20fe75a0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "577dcb54743bed4873ea5a6e8e0de060c601c31d4260fc523bcbefd8f231d56d", "generation_seconds_batch": 25.18875556497369, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01547570526599884, "target_z": -0.3378906262557939, "ce": 5.974957466125488, "genuineness": 4.833701133728027, "identity": 0.6688549518585205, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/898ad1ec715ff650ccf48c6ca5ebd3ddbb1e0e19c2f7169e7d67683d20fe75a0.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": "89f16b16d5b08106db24ce3a659d1eb8649bb6ffb44c6657f567116f79135dac", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "db3e50e2081ff3c32aed840b66d29e6635335d85bb90892ca3da4b5a6736c3e1", "generation_seconds_batch": 18.343291722936556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.059483014047145844, "target_z": -0.2031249966512162, "ce": 6.268836498260498, "genuineness": 4.331617832183838, "identity": 0.5820611715316772, "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_Intoxication_Altered_States_of_Consciousness/89f16b16d5b08106db24ce3a659d1eb8649bb6ffb44c6657f567116f79135dac.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "8a0df05d15453e10f7e4b6902ce0e5e9a8e5da70b2d470c36ee9e782241c7bba", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7d37f74291a1f8fe67d7a62c3eae34e23ff06f3fa90f213651687a001a5c1961", "generation_seconds_batch": 23.57107168796938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02146047353744507, "target_z": -0.2714843770929899, "ce": 6.157639026641846, "genuineness": 4.545003414154053, "identity": 0.6385266780853271, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/8a0df05d15453e10f7e4b6902ce0e5e9a8e5da70b2d470c36ee9e782241c7bba.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "8a317eefe621a6e5a2b9f4aa89791ce8b6b7f6db8ffb6144312b42870c57deed", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "238c65d7a478ac11625af3135140a2f713a5e059e0258a796e27cc71d582c2d7", "generation_seconds_batch": 16.68350203090813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23058442771434784, "target_z": 0.1044921818489273, "ce": 6.149696350097656, "genuineness": 4.381826400756836, "identity": 0.5973924398422241, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/8a317eefe621a6e5a2b9f4aa89791ce8b6b7f6db8ffb6144312b42870c57deed.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "8a3d83230925aba0b1935ae60c20640fd3d7cc6f3604aeb8824df63eaaafe1ca", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4cb07fc9cd51adbf1a50ada0313f104291bce8c2e36c33eea8beec9e72fb75df", "generation_seconds_batch": 18.945048050954938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0491626113653183, "target_z": -0.2216796835233192, "ce": 5.478540420532227, "genuineness": 4.482243061065674, "identity": 0.7602832317352295, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/8a3d83230925aba0b1935ae60c20640fd3d7cc6f3604aeb8824df63eaaafe1ca.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "8ae4d55ae84e8b6d8d5bbcb62a46b660346be137eb10963241f3a86601101f34", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9306b196bbf0352a03283dfcb7c60537fbc480766837bb7328dce68e117607b5", "generation_seconds_batch": 23.18378317297902, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5439987778663635, "target_z": 0.6679687541859798, "ce": 6.062326908111572, "genuineness": 4.344170093536377, "identity": 0.43296071887016296, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/8ae4d55ae84e8b6d8d5bbcb62a46b660346be137eb10963241f3a86601101f34.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "8b1b55ecd537a6c8472ddf8c5443b834b5fa67c0ac74820896c3736dc5773172", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a0adbd0788c4c505cf4b06cdf1a9004fa90cb0806cc1ed194637de9891ad2be5", "generation_seconds_batch": 17.586815714021213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 6.022613525390625, "genuineness": 4.6705241203308105, "identity": 0.610052764415741, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/8b1b55ecd537a6c8472ddf8c5443b834b5fa67c0ac74820896c3736dc5773172.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "8b3697ba51515f268d939ecafff01e08416504af227eae52d1ba41cf8a6df455", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "74fb506867bf820acdb4d422d15aa2967d0284ef266ed360e9a3f3e7aa79a420", "generation_seconds_batch": 23.57007114600856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04264445602893829, "target_z": -0.23339844440686663, "ce": 6.046441555023193, "genuineness": 4.256305694580078, "identity": 0.4772697687149048, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/8b3697ba51515f268d939ecafff01e08416504af227eae52d1ba41cf8a6df455.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "8b58a029ae3c663866c647416307f0cf4c7b284f4f9579fe70ab08dd57e6a322", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7d85d79a71a67304d0508a967bd14e88f7b27fc930434c2de3debbc8e329e24f", "generation_seconds_batch": 23.44004193600267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06165573000907898, "target_z": -0.19921874748841215, "ce": 6.1894097328186035, "genuineness": 4.65797233581543, "identity": 0.5309131145477295, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/8b58a029ae3c663866c647416307f0cf4c7b284f4f9579fe70ab08dd57e6a322.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": "8b61d15edbb93b948ebe99c490fefb2b7c7a8bfebcf1446ba5cd579c07870584", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "95e63374265cfc13a00b7484c3e6a1b1c6beec2ec4b24f663ba30d697c73ab5d", "generation_seconds_batch": 24.219618072966114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011683255434036255, "target_z": -0.28906249162804043, "ce": 6.165581703186035, "genuineness": 4.595211505889893, "identity": 0.1944597065448761, "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_Intoxication_Altered_States_of_Consciousness/8b61d15edbb93b948ebe99c490fefb2b7c7a8bfebcf1446ba5cd579c07870584.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "8b73a6092c094935e5f0be0ca5ebf58483d759f96f4ad76ccb45f999e45077ed", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f2312e33c515f9da5bc0e5abf46e19d08f9a9ba6f0d3d5ccc5b2b2f2e3f510ce", "generation_seconds_batch": 18.673003591946326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010596886277198792, "target_z": -0.2910156363021454, "ce": 6.062326908111572, "genuineness": 4.632867813110352, "identity": 0.24820224940776825, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/8b73a6092c094935e5f0be0ca5ebf58483d759f96f4ad76ccb45f999e45077ed.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "8bb32aa603fa8baf070fa6c4dadece0a8637040bb1e12e0a6b7303f713741237", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6096e13b48d595272618087288b91779267a43ed05651c08a67daefef93920a5", "generation_seconds_batch": 22.64112412300892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007871195673942566, "target_z": -0.3242187474884121, "ce": 6.046441555023193, "genuineness": 4.921566009521484, "identity": 0.7186720371246338, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons garder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/8bb32aa603fa8baf070fa6c4dadece0a8637040bb1e12e0a6b7303f713741237.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "8c3a836a168c6b088d8ab3f1451746ee4fd70f61d6fba0d7aba275cb77bc444b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8d6966c70d736d3cef2824168fead58e2e8c67689fd1adad4604c72848723f3e", "generation_seconds_batch": 22.78294626902789, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.000819668173789978, "target_z": -0.308593750837196, "ce": 5.990842819213867, "genuineness": 4.432034492492676, "identity": 0.49971437454223633, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/8c3a836a168c6b088d8ab3f1451746ee4fd70f61d6fba0d7aba275cb77bc444b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "8d1eef363191bc169aafb5b2f610df74df2a672c63ccf269b9cbbb0306f2ed9f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "33120b19007f7bace5d55284f8197b2d654bc9f6ee7b6cb56b7c1480770e0775", "generation_seconds_batch": 25.14003791997675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.041558101773262024, "target_z": -0.235351562290701, "ce": 5.720792293548584, "genuineness": 4.7332844734191895, "identity": 0.7744612097740173, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/8d1eef363191bc169aafb5b2f610df74df2a672c63ccf269b9cbbb0306f2ed9f.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": "8d404a8c4dada8b81217f37d6683ea9df79720c0b4d097831c2d46b64848ffb2", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "407c73d7577f2ce316783de2b2836ea5ff0481ed317bce12c096d5fad422a218", "generation_seconds_batch": 18.518555530929007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012769609689712524, "target_z": -0.2871093737442061, "ce": 6.38797664642334, "genuineness": 4.6203155517578125, "identity": 0.39940956234931946, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/8d404a8c4dada8b81217f37d6683ea9df79720c0b4d097831c2d46b64848ffb2.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "8d651d6b431db8495591efd2308ceb8f33dca046feff5a9ac89340789c42c282", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "12b2ed31816b13b918aec06d90e8320c405a612a969135d2de38e4639543bd1f", "generation_seconds_batch": 28.60933845001273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.268836498260498, "genuineness": 4.432034492492676, "identity": 0.4737580120563507, "hypothesis": "I found the little box. It was beside the old's window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/8d651d6b431db8495591efd2308ceb8f33dca046feff5a9ac89340789c42c282.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "8de8bfd94df3d27979f1b182e5c325d54b03532bace3cc08d2fefa8a718b3977", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b0e298224f625278dbe4c25a953e8ab92e594e2e6fb731a7618ae931a287e3b1", "generation_seconds_batch": 25.97859326703474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.109982967376709, "genuineness": 4.7332844734191895, "identity": 0.6312910914421082, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/8de8bfd94df3d27979f1b182e5c325d54b03532bace3cc08d2fefa8a718b3977.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "8f29be606b19b593d5d152f51b4fe9642a5fd64226231718a088b109ffac2607", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1d63e5c48c258a465d7e5e9861fd79dccf7a2ae842898cdc97f49b6962d85424", "generation_seconds_batch": 32.8548552809516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01438935101032257, "target_z": -0.33593750837195957, "ce": 6.086154937744141, "genuineness": 4.532451152801514, "identity": 0.6833968162536621, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/8f29be606b19b593d5d152f51b4fe9642a5fd64226231718a088b109ffac2607.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "8f8ff04ad55ae5ef27880005d6e9f37ab51fbbdd248559c65b49b1af920dd51e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "694fb9045cae7624a035a1029254b4b404f0802a43f1de2a6d4f7e9b1b82da7f", "generation_seconds_batch": 23.183982342015952, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010596886277198792, "target_z": -0.2910156363021454, "ce": 6.165581703186035, "genuineness": 4.632867813110352, "identity": 0.7055877447128296, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/8f8ff04ad55ae5ef27880005d6e9f37ab51fbbdd248559c65b49b1af920dd51e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "8f9ad77fbf44c4b3c8bd5361af3d3a994d7c4ec93b6032122d8954ce93b0091f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "eb28e93d25a3fd0c94de03b64bd1b967e5eae54971134f57c4780e47a5f70f6b", "generation_seconds_batch": 17.92101502593141, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06382844597101212, "target_z": -0.1953124983256081, "ce": 5.557967185974121, "genuineness": 4.124508857727051, "identity": 0.1346903145313263, "hypothesis": "De deur staat nog open. Ik heb je juist op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/8f9ad77fbf44c4b3c8bd5361af3d3a994d7c4ec93b6032122d8954ce93b0091f.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "8fdd6988bb37cb0fe39e457e23cca8e62280b0be4633f2bf00956f7eb77aa365", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6546f8b5734d403095498862b92b80e80b092c10be70938b07526a1f60e2e418", "generation_seconds_batch": 23.34453263389878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.038842201232910156, "target_z": -0.24023438379055753, "ce": 5.959072113037109, "genuineness": 4.287685871124268, "identity": 0.6024836301803589, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/8fdd6988bb37cb0fe39e457e23cca8e62280b0be4633f2bf00956f7eb77aa365.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "903a070cd8fa7f0cd9058ca605c718cdbdd0b0cc49a51174f64c8c341aeb6c0a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "4188bce426b6b1a51590cab70439434c6c6f90d5cbac699e09086484b6367111", "generation_seconds_batch": 19.08214870095253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016028687357902527, "target_z": -0.2812499933024324, "ce": 6.157639026641846, "genuineness": 4.432034492492676, "identity": 0.7480700016021729, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd wanneer je klaar bent.", "wer": 0.10526315789473684, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/903a070cd8fa7f0cd9058ca605c718cdbdd0b0cc49a51174f64c8c341aeb6c0a.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": "906e3004e323949c636923d8d587fa1bcd2856a2c427fb7500c809eab801dac0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "aef6528333571dc1258123d62fcd2f5fc9e91ce5709f44f70cf7c6905d1ba31b", "generation_seconds_batch": 31.11110222293064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13905875384807587, "target_z": -0.060058589250071744, "ce": 5.700935363769531, "genuineness": 4.432034492492676, "identity": 0.6604340076446533, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/906e3004e323949c636923d8d587fa1bcd2856a2c427fb7500c809eab801dac0.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": "90f5c60ca5577898d338bf0976ea8111f3763769626fc5752e87947b7265d742", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "50a66565fed6b57d9f7f164158c29bf14b35e9913b0e5760145dd973b547ae80", "generation_seconds_batch": 18.637672291020863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07197613269090652, "target_z": -0.1806640606163091, "ce": 6.125868320465088, "genuineness": 4.319066047668457, "identity": 0.5728640556335449, "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_Intoxication_Altered_States_of_Consciousness/90f5c60ca5577898d338bf0976ea8111f3763769626fc5752e87947b7265d742.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "90ffe00494cdd70f7ef058528143fd92e5c5e057097fea64033367529e5fe67e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "27969996ead60c6c0515204b152601bb702f6a34becf995f1501122f160d984f", "generation_seconds_batch": 23.90162192704156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.24500846862793, "genuineness": 4.356721878051758, "identity": 0.28057292103767395, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/90ffe00494cdd70f7ef058528143fd92e5c5e057097fea64033367529e5fe67e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "916e9fe426f6af9ab71ed1c2e893584148af0ddb8fecb66f2fc86522d6fcac5e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "91a099972c1a63fdd05da7398291044d7249b3a986d9766147ae06461c3f4b94", "generation_seconds_batch": 25.37264215608593, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07686474174261093, "target_z": -0.1718750033487838, "ce": 5.6254801750183105, "genuineness": 4.607763767242432, "identity": 0.6794140338897705, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/916e9fe426f6af9ab71ed1c2e893584148af0ddb8fecb66f2fc86522d6fcac5e.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": "91ae1870a89d582e7649e558591b121d503a31e221445dfbb355de2e723fd80c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4abc7e36e23c2e22d2321f56977b9bd6ae0da5c5761730e4693acf67a8520a40", "generation_seconds_batch": 25.015520383953117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.059483014047145844, "target_z": -0.2031249966512162, "ce": 6.0146708488464355, "genuineness": 4.883909225463867, "identity": 0.7975173592567444, "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_Intoxication_Altered_States_of_Consciousness/91ae1870a89d582e7649e558591b121d503a31e221445dfbb355de2e723fd80c.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": "92446d5d62e2d2a257503f23747b4880c5da4f938aa6f96b473a8af9517ba6cc", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "4ce0b04798520c485548a3bc581f372fe8b349e1b4613363bc5c3235c1dc12fd", "generation_seconds_batch": 17.101329975994304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03721266984939575, "target_z": -0.2431640606163091, "ce": 5.959072113037109, "genuineness": 4.6203155517578125, "identity": 0.7729411125183105, "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_Intoxication_Altered_States_of_Consciousness/92446d5d62e2d2a257503f23747b4880c5da4f938aa6f96b473a8af9517ba6cc.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "92f25482e67c43c19383e52f7f2f95b6e20829adc1598c4ac96fe021258b0a2b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e7eed73b58906f3ac72395df10c80946d0b6a3de0f15b54dc86cceaab65975c3", "generation_seconds_batch": 23.67893301998265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04318763315677643, "target_z": -0.23242188546494943, "ce": 5.967014789581299, "genuineness": 4.6705241203308105, "identity": 0.6363900899887085, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/92f25482e67c43c19383e52f7f2f95b6e20829adc1598c4ac96fe021258b0a2b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "93d317fe999af5e97f1079d4b2496e1eed1ca674ecea92c41c41796055888ad8", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9869c83b076eb55ec830bd1e2a2e2cf20b4878b265298ab502ca900263854acd", "generation_seconds_batch": 24.52919395104982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 5.8875885009765625, "genuineness": 4.68307638168335, "identity": 0.6683648824691772, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/93d317fe999af5e97f1079d4b2496e1eed1ca674ecea92c41c41796055888ad8.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "93e9781cfce62ab4e00f1e93d639139fe2af3ed845a735bc9d7126507e11f54b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5b49d9f86cec14349e1c761047163d7c1a624af0bcd3cebfe8d70a5062dcbb7d", "generation_seconds_batch": 24.270075167994946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03666949272155762, "target_z": -0.2441406195582263, "ce": 6.0146708488464355, "genuineness": 4.595211505889893, "identity": 0.5120453238487244, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/93e9781cfce62ab4e00f1e93d639139fe2af3ed845a735bc9d7126507e11f54b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "943194b428c73526968af7b927aba7bacbd5ee4896e35d3760dabd085c0b8214", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "af58d0c8bf951458a497b6e9ecff2cb14ce238f30005b2b80388915a7b90ce98", "generation_seconds_batch": 23.44004193600267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06274208426475525, "target_z": -0.19726562960457775, "ce": 6.229123115539551, "genuineness": 4.6705241203308105, "identity": 0.5995715260505676, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/943194b428c73526968af7b927aba7bacbd5ee4896e35d3760dabd085c0b8214.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "94bd79c492d70d6a498fd7ef42443ad6b7f65f57eb57d5d2d6435da6f547f292", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "550e80c6df9329e23b72437843c1f0ee7ae2e025c45db1979c68b23937309c28", "generation_seconds_batch": 23.90098298189696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04210127890110016, "target_z": -0.2343750033487838, "ce": 6.316492557525635, "genuineness": 4.796044826507568, "identity": 0.7036930322647095, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/94bd79c492d70d6a498fd7ef42443ad6b7f65f57eb57d5d2d6435da6f547f292.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "94caf055ac7c8e8d8a8b883072ea37b909112d8dcd52054c3460549390d7cd60", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "923b6b7a6fe3638d851d00916f6a82f2ecc2c01348cc43470bcc71c3d2c4d099", "generation_seconds_batch": 23.419560850947164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016028687357902527, "target_z": -0.2812499933024324, "ce": 6.1020402908325195, "genuineness": 4.394378662109375, "identity": 0.5876500606536865, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/94caf055ac7c8e8d8a8b883072ea37b909112d8dcd52054c3460549390d7cd60.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "94d07899ea407d743c40612836ea71c096ce6f922da0d53b36a57f73bacb8a30", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f017263990effc0306a7b375a17730adbe6762f75e621ee5fcc07dffd6fa86a4", "generation_seconds_batch": 20.166368718026206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09804873168468475, "target_z": -0.1337890572675253, "ce": 5.752562999725342, "genuineness": 4.645420074462891, "identity": 0.4908764958381653, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/94d07899ea407d743c40612836ea71c096ce6f922da0d53b36a57f73bacb8a30.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": "94dd7f170c355ce22bad33fdff9d0b09cb0fecf573f5c8931a5b6fa5c9e995f0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "94ed27efb0ef9a944f4a345fbfe9cd582ca2b928e4e967317185776376b55437", "generation_seconds_batch": 15.795298348995857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04318763315677643, "target_z": -0.23242188546494943, "ce": 5.816103935241699, "genuineness": 4.7332844734191895, "identity": 0.640160083770752, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/94dd7f170c355ce22bad33fdff9d0b09cb0fecf573f5c8931a5b6fa5c9e995f0.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": "9511eb2a5c2b5c8a218c5d0976364825a5d42faa516c8e321c8922589d9942a4", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8568579b8cdfe2899e224ca6310768220f7f3d14cef97e15eb528d083717dd00", "generation_seconds_batch": 18.140902928076684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06926023960113525, "target_z": -0.18554686872103035, "ce": 5.7406487464904785, "genuineness": 4.7458367347717285, "identity": 0.5899311304092407, "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_Intoxication_Altered_States_of_Consciousness/9511eb2a5c2b5c8a218c5d0976364825a5d42faa516c8e321c8922589d9942a4.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "9527b1212852c1eb5ca07501361b586a168110d291c7f6d2c296d0587915a092", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d8f895648c6ea27f47655fafcbe728199e143eea236fefc0d9e2982b767e369a", "generation_seconds_batch": 23.570920257014222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054051220417022705, "target_z": -0.21289062625579394, "ce": 5.808161735534668, "genuineness": 4.507347106933594, "identity": 0.5994577407836914, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/9527b1212852c1eb5ca07501361b586a168110d291c7f6d2c296d0587915a092.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "9604360cc44adb67062bbca50ee2cdc157dd63ed7423d01a0fdb8b8e7a53d3fe", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f38fe624dd5cf4ca2836a79aeed2a675cf820a4976a8b4aa975d435ee3cad917", "generation_seconds_batch": 18.989834381034598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0236331969499588, "target_z": -0.2675781145350506, "ce": 6.078212261199951, "genuineness": 4.406930446624756, "identity": 0.5903578996658325, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/9604360cc44adb67062bbca50ee2cdc157dd63ed7423d01a0fdb8b8e7a53d3fe.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "9659112a76722dcc3cb713fc1dd75dcf7b4b4a9c56931f13c8bb541f324712da", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c42c4ac29130471695c0b1ee922724475eb05ff84a7ffb6055c5b72fac6b0935", "generation_seconds_batch": 23.85126693500206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012769609689712524, "target_z": -0.2871093737442061, "ce": 6.006728172302246, "genuineness": 4.582659721374512, "identity": 0.7638583779335022, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/9659112a76722dcc3cb713fc1dd75dcf7b4b4a9c56931f13c8bb541f324712da.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "96921ff99b05a72f45ef6cdf1de268506fe4b2fe22e67fb76dbb025fc4be4c1a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1e1373176a19639a2341f98db7c0863a142db585aaf22b81f585f736f2ee06e8", "generation_seconds_batch": 22.554779938072897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009510532021522522, "target_z": -0.2929687541859798, "ce": 5.903473377227783, "genuineness": 4.883909225463867, "identity": 0.8683353662490845, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/96921ff99b05a72f45ef6cdf1de268506fe4b2fe22e67fb76dbb025fc4be4c1a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "96984d49f0113fc10c144ca821458ce1654f73a4a82c413c56bf81166a294325", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2ea947f95d3a075e92ddce6053e2e42e56cfdcf9df5ac039683899d17307ac66", "generation_seconds_batch": 23.451000410947017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.010043919086456299, "target_z": -0.3281250100463515, "ce": 5.911416053771973, "genuineness": 4.7332844734191895, "identity": 0.8292903304100037, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/96984d49f0113fc10c144ca821458ce1654f73a4a82c413c56bf81166a294325.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "96a6e423c9fe1b787693ec75952cceec17540579683cee0746d25eb905443fe3", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7c57af9ef92d35dc7760f259f0b22c52e50a1bbdeca1a282649c8b80e5b517e6", "generation_seconds_batch": 18.51549864804838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08881468325853348, "target_z": -0.15039062625579394, "ce": 5.990842819213867, "genuineness": 4.821148872375488, "identity": 0.7052143812179565, "hypothesis": "La porte est encore ouverte. J'ai j'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/96a6e423c9fe1b787693ec75952cceec17540579683cee0746d25eb905443fe3.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "96e001135ce81f35f49c4a6cfb42cae6bbc5983becceb2eaea3f80aaaff6e229", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "207e82dde1de7f0a84cd43bf50786c1136984f659865915867b7b5fb536da06b", "generation_seconds_batch": 24.424136615009047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014942318201065063, "target_z": -0.2832031379765373, "ce": 6.133810997009277, "genuineness": 4.532451152801514, "identity": 0.21302196383476257, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/96e001135ce81f35f49c4a6cfb42cae6bbc5983becceb2eaea3f80aaaff6e229.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "96e48858af4126dcbda51680847e57dadab283ffa2e6bb31b80e7a820441542a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fff437f815be25b5e4f6d8ea46ac8d334c612c2d77e282d69c5663150c22d77e", "generation_seconds_batch": 23.431428688927554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03612631559371948, "target_z": -0.2451171785001435, "ce": 6.173524379730225, "genuineness": 4.557555198669434, "identity": 0.4791686236858368, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/96e48858af4126dcbda51680847e57dadab283ffa2e6bb31b80e7a820441542a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "96f4264a8fc0086d93fa071e0b2e527f311c4f115ba1c4a4c06e76bd69dd9698", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6c4cb51359f01ce447241670786d2e202ad29687035cec1c7518ea2badcd400f", "generation_seconds_batch": 22.562676310073584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18875963985919952, "target_z": 0.029296875418597976, "ce": 6.0146708488464355, "genuineness": 4.883909225463867, "identity": 0.656394362449646, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/96f4264a8fc0086d93fa071e0b2e527f311c4f115ba1c4a4c06e76bd69dd9698.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "9724382c3724c849584384a8af279ff33be0f99b654b3b20374e84f3ec662395", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8d2d83907bf6a948d1f15ea864cedfa18d03c560befaf523150c73c655ab4623", "generation_seconds_batch": 22.725624848040752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0024394094944000244, "target_z": -0.3144531312789697, "ce": 6.41180419921875, "genuineness": 4.846253395080566, "identity": 0.3816438317298889, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/9724382c3724c849584384a8af279ff33be0f99b654b3b20374e84f3ec662395.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "97e26324fdb5a81c1019ec3844a590136c2420ff9d8c31a7acf3ef843d5c22ae", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "77123b458f15cb0837b493fd550cd6e480a21ac60be5caa7eeae5ddb8c3b05e2", "generation_seconds_batch": 16.812836272991262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06382844597101212, "target_z": -0.1953124983256081, "ce": 5.911416053771973, "genuineness": 4.469690799713135, "identity": 0.6214770674705505, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/97e26324fdb5a81c1019ec3844a590136c2420ff9d8c31a7acf3ef843d5c22ae.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "97fad6677e0fff7776e4d6d80465ca609ce94426bb0c691f24d6541dbc81cc71", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5bbead130e4b4613d263e30e5f201556433269942535d6dbaf0b6e03f0dd49fd", "generation_seconds_batch": 24.584105025976896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009510532021522522, "target_z": -0.2929687541859798, "ce": 6.181467056274414, "genuineness": 4.381826400756836, "identity": 0.5600778460502625, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/97fad6677e0fff7776e4d6d80465ca609ce94426bb0c691f24d6541dbc81cc71.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "987c2c18cedd69e5f0d4ffd96ba81d9b6bc57e18dcb27394a46b0c78c2b1de49", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "99b4f6c803ab851cf4a70a4c7a0c4155865f38964a6fe56885eebc593341967e", "generation_seconds_batch": 19.166680127964355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.324435234069824, "genuineness": 4.645420074462891, "identity": 0.6331692934036255, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/987c2c18cedd69e5f0d4ffd96ba81d9b6bc57e18dcb27394a46b0c78c2b1de49.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "98c5d64fb2272c3d64e05f31143de82d5f3f3d8a2985828072d9ba5bc191bb36", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ffce3cd9ad7fed9155815c698e240792cf896fe6471a58ca37bd6350c0514cb1", "generation_seconds_batch": 23.220441650017165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002992391586303711, "target_z": -0.3046874882792566, "ce": 6.157639026641846, "genuineness": 4.325342178344727, "identity": 0.6962074041366577, "hypothesis": "Ja, ik heb het kleine 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_Intoxication_Altered_States_of_Consciousness/98c5d64fb2272c3d64e05f31143de82d5f3f3d8a2985828072d9ba5bc191bb36.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "99215133b040a437c5e7aa395638aa8fd7106335f2ee7454205e7308a0237ed7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "77db5067052ee7b41bd290a51a200b533e5d9683776025e27565ab4c432e168e", "generation_seconds_batch": 24.53392719500698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03558313846588135, "target_z": -0.24609373744206067, "ce": 6.252951145172119, "genuineness": 4.6956281661987305, "identity": 0.6965221166610718, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/99215133b040a437c5e7aa395638aa8fd7106335f2ee7454205e7308a0237ed7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "9949348560aaa14b77140deda39b6872682ffd007f88e3e15a274ddca263fdee", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5cf5f523147970c2adb491f1ee34c88f4dc7275cbbb7be6d81ee957263a1d51d", "generation_seconds_batch": 21.85392303694971, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0040787458419799805, "target_z": -0.3027343703954222, "ce": 6.078212261199951, "genuineness": 4.7081804275512695, "identity": 0.675496518611908, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/9949348560aaa14b77140deda39b6872682ffd007f88e3e15a274ddca263fdee.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "99597b6dbaaca5f8e2454700cfc0e6a7be07ff93e10bcaf0dc45ff4f4d6b9539", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "47e9b0af80d74178df4de8de41b3ef0f7ffb794c90764a91995796a682e2894a", "generation_seconds_batch": 18.36596945405472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011683255434036255, "target_z": -0.28906249162804043, "ce": 5.974957466125488, "genuineness": 4.645420074462891, "identity": 0.6036733984947205, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/99597b6dbaaca5f8e2454700cfc0e6a7be07ff93e10bcaf0dc45ff4f4d6b9539.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": "997326e85c0678fce6952e9a69fa39b6da710bf62f0402847dcad4d14f176b9a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c36886922503e9fae8bd3609046e3c43703faf826b54b3854780d70b2e323646", "generation_seconds_batch": 31.11110222293064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03503994643688202, "target_z": -0.24707032317424843, "ce": 5.756534099578857, "genuineness": 4.607763767242432, "identity": 0.543928861618042, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/997326e85c0678fce6952e9a69fa39b6da710bf62f0402847dcad4d14f176b9a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "99a5a2bb286afa434631561f9c001b21c16fdec7db47b49f4047f846567b31d6", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9e59e687119ad41122813e1c535cbb232c47a753eb1ca5005b744064ba9e9922", "generation_seconds_batch": 23.96797613799572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.340320587158203, "genuineness": 4.645420074462891, "identity": 0.5768029689788818, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/99a5a2bb286afa434631561f9c001b21c16fdec7db47b49f4047f846567b31d6.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "a83d91d31278d5c5cc5fd2790756caca207420b791fae587e58f38679a46ffb1", "generation_seconds_batch": 19.07643052295316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.038842201232910156, "target_z": -0.24023438379055753, "ce": 6.38003396987915, "genuineness": 4.532451152801514, "identity": 0.3805377781391144, "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_Intoxication_Altered_States_of_Consciousness/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "99c4c746cd99321b428fc3bcda916409765f05f15bac05a4fc1f77f18031ba5c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f85539432561fd0694c0dc884f0e3676737cd4020326aafa9ae8941feb37144e", "generation_seconds_batch": 24.705270771984942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030151337385177612, "target_z": -0.2558593804417737, "ce": 6.268836498260498, "genuineness": 4.6203155517578125, "identity": 0.4626314640045166, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/99c4c746cd99321b428fc3bcda916409765f05f15bac05a4fc1f77f18031ba5c.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "9a0762fa08350cb5a9fe2c3ba4a5506e3d26788133c31ed9ff853e19736c40bd", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2f02fb7057d1326efeb3ec3ed116eaf7713a9cf99a88eda876356e4f375573e7", "generation_seconds_batch": 23.772893731016666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007337823510169983, "target_z": -0.2968749899536485, "ce": 6.260893821716309, "genuineness": 4.65797233581543, "identity": 0.6854745745658875, "hypothesis": "Jij, ik heb het kleine 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_Intoxication_Altered_States_of_Consciousness/9a0762fa08350cb5a9fe2c3ba4a5506e3d26788133c31ed9ff853e19736c40bd.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "9a3cb1218403f766e1518a244908ba6ac09a40608fc978e75b88e0c7f386fb12", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "338712267aa801deb8ecbd456589cd21fb14af5b080c4c0ee8fc7241309554a6", "generation_seconds_batch": 24.96260817896109, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003525763750076294, "target_z": -0.316406249162804, "ce": 6.078212261199951, "genuineness": 4.808597087860107, "identity": 0.6704127788543701, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/9a3cb1218403f766e1518a244908ba6ac09a40608fc978e75b88e0c7f386fb12.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "9a68bc53002f57ba4b0374952a0c3a9f0590526bcd15fc97317bde3f7322fce4", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "40b60a7e5103515c40c8ab11a461979b2deed0bc23ca32a0786955879cb157b9", "generation_seconds_batch": 19.43446201097686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007337823510169983, "target_z": -0.2968749899536485, "ce": 6.125868320465088, "genuineness": 4.7081804275512695, "identity": 0.77960205078125, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/9a68bc53002f57ba4b0374952a0c3a9f0590526bcd15fc97317bde3f7322fce4.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": "9a766e8f851f05584c2b896518e073a9c3842040bc0de209f93e23e974c8ef8b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "984c74b88336ec2081917bd00f722f623c7a6324e15abd480842ca0c842dee5d", "generation_seconds_batch": 25.609408512013033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054051220417022705, "target_z": -0.21289062625579394, "ce": 6.1020402908325195, "genuineness": 4.821148872375488, "identity": 0.5948773622512817, "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_Intoxication_Altered_States_of_Consciousness/9a766e8f851f05584c2b896518e073a9c3842040bc0de209f93e23e974c8ef8b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "9bc1de92f7fd184b33f0cfd6dd9a2b71aea3708efb9603d0fd7d85e03a3c5d76", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ed9e45686fc7d274b4cf2221a1cbedce58e9b9e10c24cf95ff80613fb9aba6df", "generation_seconds_batch": 25.151524547021836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003525763750076294, "target_z": -0.316406249162804, "ce": 5.998785495758057, "genuineness": 4.595211505889893, "identity": 0.8583494424819946, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/9bc1de92f7fd184b33f0cfd6dd9a2b71aea3708efb9603d0fd7d85e03a3c5d76.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "9be438f37adc8c9ad1828106115058ca629cd7b31ccc868d80692e088f4e0873", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c1c2716729fb504c0656806fc8b431907feca09c422422c6b77b6babff83aee7", "generation_seconds_batch": 17.90225799102336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0019060224294662476, "target_z": -0.3066406329533616, "ce": 6.054384231567383, "genuineness": 4.507347106933594, "identity": 0.6481103897094727, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/9be438f37adc8c9ad1828106115058ca629cd7b31ccc868d80692e088f4e0873.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "8da3458e77da606d5d544417f736478e515025106fe0976ca4c77420b4d66a76", "generation_seconds_batch": 20.397069229045883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012769609689712524, "target_z": -0.2871093737442061, "ce": 6.141753673553467, "genuineness": 4.381826400756836, "identity": 0.7910439372062683, "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_Intoxication_Altered_States_of_Consciousness/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.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": "9c495a0409b08be353c61be4e0609557474e6b405232d11bac3e8a6a1e13fa3d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d0ecca59b2e01e3c51dd7963d059a7aea89543ad1aa2975ebc7ccfcc58f95510", "generation_seconds_batch": 23.310212840908207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09261693805456161, "target_z": -0.14355468687210304, "ce": 6.125868320465088, "genuineness": 4.645420074462891, "identity": 0.5494186878204346, "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_Intoxication_Altered_States_of_Consciousness/9c495a0409b08be353c61be4e0609557474e6b405232d11bac3e8a6a1e13fa3d.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "8472b79a358312a149feca12669bf0022c58a3c4d4efa3198599b5a7d4a6ca5c", "generation_seconds_batch": 16.638545169029385, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 6.09409761428833, "genuineness": 4.080576419830322, "identity": 0.5592429637908936, "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_Intoxication_Altered_States_of_Consciousness/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "9cf3b350cf86eaa4c274d5c8708f5139e9754e23c5ce10b06d88f0fcb165048d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "99aa3cbd823621f06f0b475f86a506c26798135a8feba4687e7a74bcdf817670", "generation_seconds_batch": 24.981380708049983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016028687357902527, "target_z": -0.2812499933024324, "ce": 5.935244083404541, "genuineness": 4.18099308013916, "identity": 0.2624970078468323, "hypothesis": "the 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_Intoxication_Altered_States_of_Consciousness/9cf3b350cf86eaa4c274d5c8708f5139e9754e23c5ce10b06d88f0fcb165048d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "9d3665bf603148acc0b1e2df0686b0a444e88a7b1bc4131cf758969d5dba1822", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "930978e898a355f834615409eb3722a0b45d77116dcb3208a015fcd913d4f27e", "generation_seconds_batch": 28.14766024996061, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03666949272155762, "target_z": -0.2441406195582263, "ce": 6.395919322967529, "genuineness": 4.758388519287109, "identity": 0.38203567266464233, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/9d3665bf603148acc0b1e2df0686b0a444e88a7b1bc4131cf758969d5dba1822.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": "9e428bb77501bf9b21c8c1b73e509347a6b12a7ef575c01a7b478006c761d38b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "1e9c56334dc964405b322b7b9874d8ab88137e83ee8bdb2ef0a3d80536ee011f", "generation_seconds_batch": 17.101329975994304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05731029808521271, "target_z": -0.20703124581402021, "ce": 5.71682071685791, "genuineness": 4.595211505889893, "identity": 0.842137336730957, "hypothesis": "La roue tourne à gauche après le pont. Continue, jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.05, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/9e428bb77501bf9b21c8c1b73e509347a6b12a7ef575c01a7b478006c761d38b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "9e502e7ae8a3b159d8ac1e04fc9a774df594229322a35854c691724ad17d7634", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c7db19062e04766ca7e1096659035a5399e4fb4d541eab52560c8848920d9fdb", "generation_seconds_batch": 23.45053272100631, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03775584697723389, "target_z": -0.2421875016743919, "ce": 5.831989288330078, "genuineness": 4.770940780639648, "identity": 0.5727807283401489, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre ! Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/9e502e7ae8a3b159d8ac1e04fc9a774df594229322a35854c691724ad17d7634.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "9e6885b336299f866e14fa2e252771a9ab2c67819296b449dd8ede9e750d7ec9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "4e7a1ae2ddfd9a0d80366419d8b83c7b1a33ac4fcfb53b3be535908156be6005", "generation_seconds_batch": 24.97923737706151, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0062514543533325195, "target_z": -0.2988281346277535, "ce": 5.990842819213867, "genuineness": 4.808597087860107, "identity": 0.5728814601898193, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/9e6885b336299f866e14fa2e252771a9ab2c67819296b449dd8ede9e750d7ec9.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "9e81b1201ecf1f01be1f907844e3eabb2a90fc7b36fb7e286f39e43052b54b64", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0af7ba3c7e87ecb0b6837a188cc551a2150aacddf07b30c9e7af38fec981eab2", "generation_seconds_batch": 24.303023175918497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013855963945388794, "target_z": -0.2851562558603717, "ce": 6.284721851348877, "genuineness": 4.720732688903809, "identity": 0.395663321018219, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/9e81b1201ecf1f01be1f907844e3eabb2a90fc7b36fb7e286f39e43052b54b64.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "9eafd5b3cea57068d790de988bf3848bb26d84c40fb6aaa97f3794ca5625a786", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2218684690695ae3b334f12fbd8666dd79a811df9d13a3d2779313d0df734011", "generation_seconds_batch": 24.350407785037532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.1020402908325195, "genuineness": 4.833701133728027, "identity": 0.8351014852523804, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/9eafd5b3cea57068d790de988bf3848bb26d84c40fb6aaa97f3794ca5625a786.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "9ed4edf65a952a03ea325c5b6fbfbeb1696101bc83e45aa91e349b1c238d5108", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "bed632ad5218cfb69a5164e6a0f5bfaefde8e6a2f54b4f1a8065ef973ea99d05", "generation_seconds_batch": 25.299864131957293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.001353040337562561, "target_z": -0.3124999866048647, "ce": 6.054384231567383, "genuineness": 4.846253395080566, "identity": 0.7365807294845581, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/9ed4edf65a952a03ea325c5b6fbfbeb1696101bc83e45aa91e349b1c238d5108.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "9ed9682cfeed76c4e672bb2905d1b69f1e3f0d4dfc4ec9e4da6d321aa3a259f4", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6cd45e6325500d6f7741d446e6b25e39eb26ffe2f409712e8f85515771f3037e", "generation_seconds_batch": 22.169364113011397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03558313846588135, "target_z": -0.24609373744206067, "ce": 5.677107334136963, "genuineness": 4.7458367347717285, "identity": 0.6639689207077026, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/9ed9682cfeed76c4e672bb2905d1b69f1e3f0d4dfc4ec9e4da6d321aa3a259f4.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "9f02fedf279a61beb26fd5b9ed684291befbe32b0169b9f606df8f25e501b078", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ae45e923a1a5661d1ec3f1c3b5a740312fcdee843fa9143a539fc13cd3bf3d58", "generation_seconds_batch": 18.74966129194945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013855963945388794, "target_z": -0.2851562558603717, "ce": 5.990842819213867, "genuineness": 4.457139015197754, "identity": 0.505181610584259, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/9f02fedf279a61beb26fd5b9ed684291befbe32b0169b9f606df8f25e501b078.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": "9f5959a5a9c2b2fedf3bbeeced4a35fd5d9c97c66cf70a9ee137e2416d165cf6", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "45ee9a67dae9d7653da2c12234cfb1ec3ce486fb9182b4d7cc8d3cec7ddb160a", "generation_seconds_batch": 23.133416485972703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.021993860602378845, "target_z": -0.34960938713934137, "ce": 6.125868320465088, "genuineness": 4.419482707977295, "identity": 0.6016188859939575, "hypothesis": "The keys are on the kitchen table. I I checked the drawer then looked beside the window. Take them with you when you leave.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/9f5959a5a9c2b2fedf3bbeeced4a35fd5d9c97c66cf70a9ee137e2416d165cf6.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "9f6e63c67fbd7d83b23452237b51700aacb552967ce0f527b99067e3745508ce", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "605aa5abe76925e22ee05f184e51bff1e0897053f37b9adb7c34d5bdb3c6c93e", "generation_seconds_batch": 23.85126693500206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011683255434036255, "target_z": -0.28906249162804043, "ce": 6.117925643920898, "genuineness": 4.607763767242432, "identity": 0.8512555956840515, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/9f6e63c67fbd7d83b23452237b51700aacb552967ce0f527b99067e3745508ce.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": "9f89619db4831eb523fbdc12381525e6017bb380733d98c82ea4c2f8c7f336cd", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "40bed544017cbd0741d72db1fe346ca266e0667a65104d485313e3c535ffbecb", "generation_seconds_batch": 17.937332532019354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06056936830282211, "target_z": -0.2011718787673818, "ce": 6.221180438995361, "genuineness": 4.921566009521484, "identity": 0.7481662631034851, "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_Intoxication_Altered_States_of_Consciousness/9f89619db4831eb523fbdc12381525e6017bb380733d98c82ea4c2f8c7f336cd.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "9fc3c8993d69bd4e7d5bcfbcb52a4c419019dc1fd6ee8b1154f1fb51fee627a5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "29b9bdc2c0b38f9c9ad4c89ded7cb1e2af209823cffab1109e1048cd2b3505c7", "generation_seconds_batch": 25.23569438594859, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03558313846588135, "target_z": -0.24609373744206067, "ce": 6.078212261199951, "genuineness": 4.413206577301025, "identity": 0.36088335514068604, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/9fc3c8993d69bd4e7d5bcfbcb52a4c419019dc1fd6ee8b1154f1fb51fee627a5.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "a0604026469b842baa1ce5a58f437bf5aef37900ea015ddfe30b2cf9754daf00", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5e5a754ae1648a0758f2e6533dd2e2625f277fbf1bd4188a955497b565a32c7d", "generation_seconds_batch": 24.886785384034738, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.010043919086456299, "target_z": -0.3281250100463515, "ce": 6.1894097328186035, "genuineness": 4.808597087860107, "identity": 0.6405130624771118, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/a0604026469b842baa1ce5a58f437bf5aef37900ea015ddfe30b2cf9754daf00.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "a069ff0efc5cb5c5fd02b3181f44ce7d9ececc688d3abbab1690eb653409c171", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b50886c3ca44c54e975c0f8f4ac88ec9092ca3bc9bb22a88700410e4abc35dcf", "generation_seconds_batch": 27.485168176004663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06056936830282211, "target_z": -0.2011718787673818, "ce": 5.7128496170043945, "genuineness": 4.632867813110352, "identity": 0.40364882349967957, "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_Intoxication_Altered_States_of_Consciousness/a069ff0efc5cb5c5fd02b3181f44ce7d9ececc688d3abbab1690eb653409c171.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "a116332d673ba2055076b56e552d0e93c2a37c7e456f74361c414cba64975288", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d030bfa9cdbbb7fdc8e92fcf6ef36758a51f54dc1b1d117a1fe83fa0caea0975", "generation_seconds_batch": 25.946683672023937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03666949272155762, "target_z": -0.2441406195582263, "ce": 5.927301406860352, "genuineness": 4.607763767242432, "identity": 0.5943700671195984, "hypothesis": "Ma porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/a116332d673ba2055076b56e552d0e93c2a37c7e456f74361c414cba64975288.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "a145ece8ba3c8e905d6eccc48734c350401d8db65c33fbd97178e7703f5e27b5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7d3d109b4b0b7514222ba341e4430cf8ed0da1e2e51dabc8107c73e0829ce087", "generation_seconds_batch": 27.834752660011873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031237691640853882, "target_z": -0.2539062625579393, "ce": 6.125868320465088, "genuineness": 4.7081804275512695, "identity": 0.6893430948257446, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/a145ece8ba3c8e905d6eccc48734c350401d8db65c33fbd97178e7703f5e27b5.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "a1712d2669c853a7f78dd0dfcde703d5f913b3fbdab25edaa61fa5190460eb6b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bd757d0704ceae44af4abde391b6bb1d3b17ea067e567f6badcd3c6a55ae3d1f", "generation_seconds_batch": 25.31448449299205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05187850445508957, "target_z": -0.216796875418598, "ce": 5.927301406860352, "genuineness": 4.419482707977295, "identity": 0.6229873895645142, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/a1712d2669c853a7f78dd0dfcde703d5f913b3fbdab25edaa61fa5190460eb6b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "a187d7d4d01fcb8e87aa44c347ff738e6517500605e574d8f7fb2eec0a43e644", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "628a42595fbdeea77ed90891989643f685ed36bb89f3c31e456aea54fb79e87e", "generation_seconds_batch": 25.40210206795018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04970578849315643, "target_z": -0.220703124581402, "ce": 5.831989288330078, "genuineness": 4.909013748168945, "identity": 0.5507020354270935, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/a187d7d4d01fcb8e87aa44c347ff738e6517500605e574d8f7fb2eec0a43e644.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "a1d79703b3109d1987bec29c28f0dd1d19fd5ef63fe48892ce500239d315b081", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3f51076effccb318ef4948d24f8578f2a1ab6dd8f0aed7ed348716024f949cb9", "generation_seconds_batch": 24.30899175896775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1996232271194458, "target_z": 0.048828134627753476, "ce": 5.919358730316162, "genuineness": 4.344170093536377, "identity": 0.5964661836624146, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/a1d79703b3109d1987bec29c28f0dd1d19fd5ef63fe48892ce500239d315b081.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "a2a016142cb73109fa5081931e91348d106de22485e68c14e271d31bb875cc50", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "642bcc4b63e41fc7ec7482a802eab4493fabc812180dd1db3992a0503dfa9ece", "generation_seconds_batch": 24.579031486995518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08338288962841034, "target_z": -0.1601562558603717, "ce": 5.927301406860352, "genuineness": 4.381826400756836, "identity": 0.5265412330627441, "hypothesis": "De deur staat nog open? Ik heb je Jas op de stoel gelegd, zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/a2a016142cb73109fa5081931e91348d106de22485e68c14e271d31bb875cc50.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "a2c97237c6500e40589f36f19631cab2705ebebb0fda405224fc16ed59e5b2ee", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f00e5baeeb05349e95da4c02fbff580927e4906f84e9295d7c42e19685c875b6", "generation_seconds_batch": 24.201779310009442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03558313846588135, "target_z": -0.24609373744206067, "ce": 6.109982967376709, "genuineness": 4.582659721374512, "identity": 0.6887763738632202, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/a2c97237c6500e40589f36f19631cab2705ebebb0fda405224fc16ed59e5b2ee.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "a2eb3f5e11805f5bac3b6ee30fa6756b2e3cf72bec35d07d6a2cdccd22868e0a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4c769d75bd1fc508f4d2be24e94a3f4a25fbec4b7219d0580ed10d89154ef31a", "generation_seconds_batch": 23.811758383992128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 5.816103935241699, "genuineness": 4.337893962860107, "identity": 0.6159744262695312, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/a2eb3f5e11805f5bac3b6ee30fa6756b2e3cf72bec35d07d6a2cdccd22868e0a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "a30fe79ad2e4aab28b0810a6df596e49fe5b4e0802db5e6538c175794f48ce81", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "2ad200e84c25b0aad0e765e530d246d4ec85bd91514f2c042f5f0ff416da8b25", "generation_seconds_batch": 23.833867309964262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03395359218120575, "target_z": -0.2490234410580828, "ce": 6.09409761428833, "genuineness": 4.432034492492676, "identity": 0.3939822018146515, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/a30fe79ad2e4aab28b0810a6df596e49fe5b4e0802db5e6538c175794f48ce81.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "a3736ff3495c2a82c5662480fa5c83a691df55b509fea357893abe59625a2129", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "fb24a90b03f5b26b2690c0890382ddb5f63b6e4acc2d71aedd5d58614890a3ec", "generation_seconds_batch": 16.141318134963512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 6.006728172302246, "genuineness": 4.720732688903809, "identity": 0.7324249744415283, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/a3736ff3495c2a82c5662480fa5c83a691df55b509fea357893abe59625a2129.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "a391d7fecb10b5c3116eb4e5ca12a34fe2d29e47be8f2897af339f23ae17175b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "19bcdc1ab50baabc47f7d796e6c7741177342d7d6039fbf0c8d1bac086d3ed6c", "generation_seconds_batch": 23.833867309964262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04373082518577576, "target_z": -0.2314452997327617, "ce": 6.006728172302246, "genuineness": 4.381826400756836, "identity": 0.5421196222305298, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/a391d7fecb10b5c3116eb4e5ca12a34fe2d29e47be8f2897af339f23ae17175b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "a3a7d50a4d81a6f9eab5d4f82a298bc61ebfd1dcf290da0ff8b46281c5bbf7f5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bb766a1b2e900b13956c49a87f2c0656ccbf91f7bead56ad90a42c3300de716d", "generation_seconds_batch": 32.46501441707369, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033410415053367615, "target_z": -0.25, "ce": 5.748591423034668, "genuineness": 4.770940780639648, "identity": 0.5691249370574951, "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_Intoxication_Altered_States_of_Consciousness/a3a7d50a4d81a6f9eab5d4f82a298bc61ebfd1dcf290da0ff8b46281c5bbf7f5.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "a437ee18f491eeeae5f0680f2f3e3d6e340bbf00797dcd5f920bc2a22e351d63", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f9bf4144a7b7cacc07b2eca7b3a58521e2e455f0633661602ab3b927ad382a6f", "generation_seconds_batch": 24.928955451003276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0779511034488678, "target_z": -0.16992187206981416, "ce": 5.824047088623047, "genuineness": 4.011539936065674, "identity": 0.1890091896057129, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/a437ee18f491eeeae5f0680f2f3e3d6e340bbf00797dcd5f920bc2a22e351d63.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "a47f8c35ae0598d496009df5285c57512c039454b19840f2549122dc79f91594", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d2527372aa1414c70389e92e72ecf21a26a57b37ccd54040775ce36b74be0597", "generation_seconds_batch": 22.847749138018116, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0236331969499588, "target_z": -0.2675781145350506, "ce": 6.252951145172119, "genuineness": 4.21237325668335, "identity": 0.346767783164978, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/a47f8c35ae0598d496009df5285c57512c039454b19840f2549122dc79f91594.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "a4a714c2d3e0fe848c3c2824dd4555b18733b4215a1e6bb6e7cb90bfe881907a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e0aa27201fbf08728ffd06827b1a2418cc74b42506f35539a736efe204ca1e8d", "generation_seconds_batch": 22.230646535987034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033410415053367615, "target_z": -0.25, "ce": 6.0146708488464355, "genuineness": 4.645420074462891, "identity": 0.7131158113479614, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/a4a714c2d3e0fe848c3c2824dd4555b18733b4215a1e6bb6e7cb90bfe881907a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "a5ac74651029a9c1f04ec77926733d56058fa1165c9498e2c01cf1c69b51b1f6", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9f7cd9c9b06d3adda361734203e851a72c50e1192a4856dc2d22098f1b01a0fd", "generation_seconds_batch": 27.015567269991152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.284721851348877, "genuineness": 4.331617832183838, "identity": 0.6001119613647461, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/a5ac74651029a9c1f04ec77926733d56058fa1165c9498e2c01cf1c69b51b1f6.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "a5f38212dde24a1ea66720ffdf91b52ce321532b27ecea2216e420cdffa35ef8", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "73130b8fd4bc35d44e170519c435f24b5411d0bd71361592228fe32b724b03af", "generation_seconds_batch": 18.258221653057262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05350804328918457, "target_z": -0.2138671851977111, "ce": 6.3641486167907715, "genuineness": 4.7834930419921875, "identity": 0.2663828730583191, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/a5f38212dde24a1ea66720ffdf91b52ce321532b27ecea2216e420cdffa35ef8.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "a6687d73ac43c145c7ee5c1f0406117a8cef583b5894f4a47909ae3350d98788", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "004c847bbaec3f413ef1a0a5500e7976876e37b468142ba76252a31393a54dda", "generation_seconds_batch": 24.201779310009442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04373082518577576, "target_z": -0.2314452997327617, "ce": 6.300607204437256, "genuineness": 4.595211505889893, "identity": 0.7104716300964355, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/a6687d73ac43c145c7ee5c1f0406117a8cef583b5894f4a47909ae3350d98788.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "a6c67b9b4647fc23befa2453f561ac6c20b7b14e78f587c32ae2a0f1e8269abf", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5645aeb513dfc87c4c37cc97619829ebd16248123569ae7df177dcbab2a84c54", "generation_seconds_batch": 24.076679519028403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04970578849315643, "target_z": -0.220703124581402, "ce": 6.165581703186035, "genuineness": 4.770940780639648, "identity": 0.4550274610519409, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/a6c67b9b4647fc23befa2453f561ac6c20b7b14e78f587c32ae2a0f1e8269abf.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "a780d5e5cb5f2b24e3a49a5e5c20fe00f2a036ac2e5388979236b0e9733fb9af", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "717ad7656de6e169c6d5fdca5e9e4fc18883425f2bb42e85b6c715eb8ea8de03", "generation_seconds_batch": 23.865155115025118, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.045903533697128296, "target_z": -0.2275390639650929, "ce": 5.998785495758057, "genuineness": 4.7458367347717285, "identity": 0.7553606629371643, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/a780d5e5cb5f2b24e3a49a5e5c20fe00f2a036ac2e5388979236b0e9733fb9af.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "a7f0e62940d7fc555d821b15f91e28c4f1b870f1f3dc8e4e62ad89c277273ce8", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "55109ee09488d5b547ca297edde9e20b6cbb9851df8a0112e2bcbb2e80ff48dc", "generation_seconds_batch": 23.656037547043525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03775584697723389, "target_z": -0.2421875016743919, "ce": 5.796247482299805, "genuineness": 4.770940780639648, "identity": 0.7622033357620239, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/a7f0e62940d7fc555d821b15f91e28c4f1b870f1f3dc8e4e62ad89c277273ce8.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "30d1a5acb7bf4b0ef64cfb8239fc11c4e7645813a91a57f2d3a72a811c1074fc", "generation_seconds_batch": 18.856498042005114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.000819668173789978, "target_z": -0.308593750837196, "ce": 6.157639026641846, "genuineness": 4.18726921081543, "identity": 0.4484441876411438, "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_Intoxication_Altered_States_of_Consciousness/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "a9462a54993d0b8f5444243d7551ed4292e6c881070e6675c78ac8a8709b9e51", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "35c7aca6fd0198bdbaf163ff088d09512a7044d449aefe605f81704a0b959337", "generation_seconds_batch": 24.892824792070314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009510532021522522, "target_z": -0.2929687541859798, "ce": 6.070269584655762, "genuineness": 3.961331605911255, "identity": 0.33552825450897217, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/a9462a54993d0b8f5444243d7551ed4292e6c881070e6675c78ac8a8709b9e51.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e6343725616572de9979395c7eb27b9fabdbd49af80c4600d89d543ec236093c", "generation_seconds_batch": 18.95929229806643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03558313846588135, "target_z": -0.24609373744206067, "ce": 6.356205940246582, "genuineness": 4.582659721374512, "identity": 0.7716899514198303, "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_Intoxication_Altered_States_of_Consciousness/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "a9f1c126384591d65280ece26eca274cc618d09554041ab7c184208fb079e9a9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "wording", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "bae0a31da9e31ce223098de58e4b0fd963f478026590c8b1bf0496633587c42a", "generation_seconds_batch": 17.4195655049989, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.018734782934188843, "target_z": -0.3437500066975676, "ce": 6.038498878479004, "genuineness": 4.7081804275512695, "identity": 0.6797637939453125, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/a9f1c126384591d65280ece26eca274cc618d09554041ab7c184208fb079e9a9.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": "a9f99fe6c758d2a85cc441f828af93467c3743d54476d3f0a1cb91eef759847f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "c86ad7d05b773fe6bd8afc2c9f7fae381ada76d96c86cce2b61e565d9e61ccc1", "generation_seconds_batch": 18.537100233021192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2729524075984955, "target_z": 0.18066407401144438, "ce": 6.181467056274414, "genuineness": 4.457139015197754, "identity": 0.5162501335144043, "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_Intoxication_Altered_States_of_Consciousness/a9f99fe6c758d2a85cc441f828af93467c3743d54476d3f0a1cb91eef759847f.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "aaba86b9c251f45cb1df939efb41556a664c31fb4e43f0f8ff62ef4a130745e7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7b316d50a9c092e7adc47a97f121a8bb364b434d87eeb815e8f7ebb1ccd15f03", "generation_seconds_batch": 23.811758383992128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07414884865283966, "target_z": -0.17675781145350505, "ce": 5.879645347595215, "genuineness": 4.607763767242432, "identity": 0.5815842747688293, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/aaba86b9c251f45cb1df939efb41556a664c31fb4e43f0f8ff62ef4a130745e7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "ab48e18b1335b9f5f15c48182d8926ffcfe1b4c062feea7f0447bb16dede0ef6", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "50ccd8a88c968b194d90dd0fbe5b0b6fb854c7957ec76ec74299209f37ebee36", "generation_seconds_batch": 25.25761707802303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016028687357902527, "target_z": -0.2812499933024324, "ce": 6.062326908111572, "genuineness": 4.632867813110352, "identity": 0.4008997678756714, "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_Intoxication_Altered_States_of_Consciousness/ab48e18b1335b9f5f15c48182d8926ffcfe1b4c062feea7f0447bb16dede0ef6.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "21f8f0bcdd843825116cb783f074f11c17ba4e6704cfdbaf6a89f9d462fb3344", "generation_seconds_batch": 15.696308327023871, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009510532021522522, "target_z": -0.2929687541859798, "ce": 6.427689552307129, "genuineness": 4.293961524963379, "identity": 0.3130066692829132, "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_Intoxication_Altered_States_of_Consciousness/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "ac844a5efc41d69a3941f32c7341c9a164747d3c482dde63538aa3b9fbecb91d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6f7d31b1b2968bef46573980d534108e6473bcf21a7936eb5273e6a4b329e18a", "generation_seconds_batch": 24.705270771984942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02580590546131134, "target_z": -0.2636718787673818, "ce": 6.308549880981445, "genuineness": 4.632867813110352, "identity": 0.384240984916687, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/ac844a5efc41d69a3941f32c7341c9a164747d3c482dde63538aa3b9fbecb91d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "acb41f25c48a972b6d7f8b10cf92f133c11b807cdecf334b2551c7c6341a112d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1443e144274cd3065b5b9b27897ca944ea09698a7b31e70f64d5ac49e0dbe06e", "generation_seconds_batch": 23.837625812040642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02689225971698761, "target_z": -0.2617187608835474, "ce": 5.990842819213867, "genuineness": 4.7081804275512695, "identity": 0.7779867649078369, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/acb41f25c48a972b6d7f8b10cf92f133c11b807cdecf334b2551c7c6341a112d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "ad482cd6a72609aa9e3747f3d71f8e0ce369f3d0beec7a8e1b0da633f9b42005", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5e0acbe732fd82bd6f5928e57dc02290db519cd2061f8ff152b960d6413242ef", "generation_seconds_batch": 25.116535856970586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 6.141753673553467, "genuineness": 4.545003414154053, "identity": 0.4695090055465698, "hypothesis": "Ik heb het kleine dookzeug 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_Intoxication_Altered_States_of_Consciousness/ad482cd6a72609aa9e3747f3d71f8e0ce369f3d0beec7a8e1b0da633f9b42005.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "ad6102f75ac7170847d794334dc53eb877ca9f27a1e0ad3b1fa11cf4e7e76491", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce3219bd864f4ad028f408892e14851519f2b6b7bd45772e8084752e19be44a3", "generation_seconds_batch": 24.29743661696557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017115041613578796, "target_z": -0.279296875418598, "ce": 6.252951145172119, "genuineness": 4.532451152801514, "identity": 0.6399186849594116, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/ad6102f75ac7170847d794334dc53eb877ca9f27a1e0ad3b1fa11cf4e7e76491.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "3c55bae3cd7e4d59694fa2249ff21bd8b4ce2c321f03e061741108b1eae248c8", "generation_seconds_batch": 16.667439923039638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0019060224294662476, "target_z": -0.3066406329533616, "ce": 6.117925643920898, "genuineness": 4.381826400756836, "identity": 0.6831241846084595, "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_Intoxication_Altered_States_of_Consciousness/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.mp3" }, { "id": "heldout-en-2", "language": "en", "sentences": [ "The road turns left behind the bridge.", "Keep going... until you reach the small wooden gate.", "I will meet you on the other side." ], "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-2", "key": "ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "640f846bcf665eaa27bce7c6cc22bc665019eae9e7ab10afa203691ecdba16c9", "generation_seconds_batch": 16.92203227209393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 6.284721851348877, "genuineness": 4.068024158477783, "identity": 0.3431188464164734, "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_Intoxication_Altered_States_of_Consciousness/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "aee5939ff327bb2c108a5326c9cb4cadd1ac104934353bdd40fb18318a659a33", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3b8bff44aecd584081afed43af6f95b9a1967c09775d8cbd39206f243d355d7f", "generation_seconds_batch": 24.884875854942948, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 6.252951145172119, "genuineness": 4.482243061065674, "identity": 0.6530849933624268, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/aee5939ff327bb2c108a5326c9cb4cadd1ac104934353bdd40fb18318a659a33.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "af1bbb9b13472345c1a3f337b02d0f7bf21f704a58a53d9f1b7a9852b47775af", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b16fca83580ad83607c4604f07cf0db7b6346b28990acfe7b34dae7646908f0d", "generation_seconds_batch": 25.45972253207583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.213237762451172, "genuineness": 4.68307638168335, "identity": 0.295407772064209, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/af1bbb9b13472345c1a3f337b02d0f7bf21f704a58a53d9f1b7a9852b47775af.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": "b038ce9643a1988c59386b803b906474e19f7d9fdd7b94134e3c4da89c4cac43", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "3d9d6770530d92a5b116ebd3fb11866726be308e3a31488e4c882ba4716005e7", "generation_seconds_batch": 20.30916432500817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07740792632102966, "target_z": -0.17089843101173136, "ce": 6.09409761428833, "genuineness": 4.632867813110352, "identity": 0.59958416223526, "hypothesis": "Escribí el número en el sobre. Lélelo bien. Y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b038ce9643a1988c59386b803b906474e19f7d9fdd7b94134e3c4da89c4cac43.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "b0461e64ab10aaf510d41b5bb35f231b5a0f6c37a457123cf8c911bbf2116ef3", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2c695469a9ffed55fa157f8d80b96f8539c70807f744adf57f91524775d202df", "generation_seconds_batch": 23.91904093802441, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12683722376823425, "target_z": -0.08203124581402023, "ce": 6.316492557525635, "genuineness": 4.519899368286133, "identity": 0.42239049077033997, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/b0461e64ab10aaf510d41b5bb35f231b5a0f6c37a457123cf8c911bbf2116ef3.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "b08e642d2b2de688a2f7f0edfd9b30b11074114d91c93e956a21d33f09c76c06", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "51651e2eaaaaafc8f572a531dea38305a9bfaee0930099a6df1b06fe0eff8e4e", "generation_seconds_batch": 17.403280145023018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09967826306819916, "target_z": -0.1308593804417737, "ce": 5.677107334136963, "genuineness": 4.293961524963379, "identity": 0.36402928829193115, "hypothesis": "De deur staat nog open. Ik heb je Jas op de stoel gelegd. Zeg maar, wanneer je klaar bent...", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b08e642d2b2de688a2f7f0edfd9b30b11074114d91c93e956a21d33f09c76c06.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "b0ac4b37da36f8408546761a51a7310b4bbdcb10cf028da6d28177a274ae4ee1", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a5247c5a81513159181c93aee7192f3983e1f8b0d8e751ccd406eaa052a169e7", "generation_seconds_batch": 18.408938145032153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009510532021522522, "target_z": -0.2929687541859798, "ce": 6.268836498260498, "genuineness": 4.8588056564331055, "identity": 0.8030840158462524, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/b0ac4b37da36f8408546761a51a7310b4bbdcb10cf028da6d28177a274ae4ee1.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "b0bdf5391a449db07dca937bf2142ca8a018082f48e7dde8cc06725d835a52de", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "98e05adb55a0c87db2bc849a04a896342773cae74430888228da45bb214a3963", "generation_seconds_batch": 17.87886647193227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05459439754486084, "target_z": -0.21191406731387674, "ce": 5.792276382446289, "genuineness": 4.7332844734191895, "identity": 0.6195081472396851, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b0bdf5391a449db07dca937bf2142ca8a018082f48e7dde8cc06725d835a52de.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "b11e4e5d46c80c1a120a2de16278b8cad9d01177eefd346697825c821627b889", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "02819ff3a63b4f0552a252b9e285252b9d962f3064b61613073e3dcf8d18ccb9", "generation_seconds_batch": 23.87242591602262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 6.427689552307129, "genuineness": 4.293961524963379, "identity": 0.5251255035400391, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b11e4e5d46c80c1a120a2de16278b8cad9d01177eefd346697825c821627b889.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "b12bec85aa799639568f4dc925e6a1fd59f05056a2a6ca355d733748f12b1687", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "wording", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d697ffd7f9b2585c27e35fe7523646f1141e943ce78b3ceb9798e057bd90e993", "generation_seconds_batch": 16.909338457975537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010596886277198792, "target_z": -0.2910156363021454, "ce": 6.109982967376709, "genuineness": 4.137060642242432, "identity": 0.19064709544181824, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b12bec85aa799639568f4dc925e6a1fd59f05056a2a6ca355d733748f12b1687.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "b157d6fdfc3548cbd8328f913bc0ca2c829f811972f0687edacbb77dca18a3f9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7bb2fdb293e7cf6fbf21abbca2b908b5a5d36526b8c3edd2b5022f021fa425bc", "generation_seconds_batch": 24.421891069971025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08175335824489594, "target_z": -0.16308593268612326, "ce": 6.070269584655762, "genuineness": 4.808597087860107, "identity": 0.6673768758773804, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b157d6fdfc3548cbd8328f913bc0ca2c829f811972f0687edacbb77dca18a3f9.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "b1ac71c4c247ae06b51575b4949de613a6f831e44f66fa431bab3264a42ed5e7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8c14cf988150c99256fe6561af25b9d4c8b562d09630b4c04ebbb4b53c28f62c", "generation_seconds_batch": 26.825475313933566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17395800352096558, "target_z": 0.0026855370902722814, "ce": 6.173524379730225, "genuineness": 4.413206577301025, "identity": 0.6934266686439514, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b1ac71c4c247ae06b51575b4949de613a6f831e44f66fa431bab3264a42ed5e7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "b2424578756448885bf00c3cc8f83ab3c3d4b5f6bad6b177a2ac31370dc96b7b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "64d1da95c81e7929c848f77db832bb459a6e889ee35337e01ecb956a7f4a9601", "generation_seconds_batch": 23.0252912879223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19948743283748627, "target_z": 0.04858399489227418, "ce": 6.070269584655762, "genuineness": 4.425758361816406, "identity": 0.5333071947097778, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen daar samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b2424578756448885bf00c3cc8f83ab3c3d4b5f6bad6b177a2ac31370dc96b7b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "b26e1a18194ac0e53e4136be1dd06bfd1880b864ec3382b12814986208c049cb", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2d52d8dfa0c9bc5add0addb4ee6252a985f0c326a10ecd4103ea9ebf3550d35e", "generation_seconds_batch": 24.12989183200989, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04427400231361389, "target_z": -0.2304687407908445, "ce": 6.316492557525635, "genuineness": 4.7081804275512695, "identity": 0.5928946137428284, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b26e1a18194ac0e53e4136be1dd06bfd1880b864ec3382b12814986208c049cb.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "b28632c0117b268058a5641062ab1d31ae925422ca390e99b93d82cbda751e6e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c989fa4ac1ce2c06226f525119d0a4ea450fd39bac14fa0c1806760e68ae6b90", "generation_seconds_batch": 24.928955451003276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011683255434036255, "target_z": -0.28906249162804043, "ce": 5.919358730316162, "genuineness": 4.469690799713135, "identity": 0.7027794122695923, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b28632c0117b268058a5641062ab1d31ae925422ca390e99b93d82cbda751e6e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "b28ea6b2b0b33edf4cb5287627364edbcff597b04f8cfca72710b140d7dd2d6e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d49fce5a8ae6c95d29ed2781beef892763da93ab2ccee5eb929c6784bb190284", "generation_seconds_batch": 25.143997850944288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.012216627597808838, "target_z": -0.3320312458140202, "ce": 6.086154937744141, "genuineness": 4.68307638168335, "identity": 0.6285775303840637, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b28ea6b2b0b33edf4cb5287627364edbcff597b04f8cfca72710b140d7dd2d6e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "b2c62ce9ad8ca5395bfe2846349a16dd1e806d284e77b1b27d441920f2f1878f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3afadc1df34fe8b2e3888915a24a795117b301e5e38590c89b8e2c1335b45f02", "generation_seconds_batch": 25.652373370015994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008957549929618835, "target_z": -0.3261718653722465, "ce": 6.23706579208374, "genuineness": 4.570107460021973, "identity": 0.743394672870636, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/b2c62ce9ad8ca5395bfe2846349a16dd1e806d284e77b1b27d441920f2f1878f.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "b2f8a52cc494ebab1f028e6e05baad6e2d9ceda3ece2aaf38d9afaf6f68b18a7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "237e8f28d07e44364cee097489c469a4ca52dd31cf7fa2442f43286a95d44332", "generation_seconds_batch": 23.12750527402386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.000819668173789978, "target_z": -0.308593750837196, "ce": 6.0146708488464355, "genuineness": 4.770940780639648, "identity": 0.734628438949585, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b2f8a52cc494ebab1f028e6e05baad6e2d9ceda3ece2aaf38d9afaf6f68b18a7.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": "b326f57872341bb3e1abfc21a29c32d1e89d47581e3d55d9478933f1837feb52", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "cd19b4a28ba26bd8176ac51ce09db02844a71ae30daf332c4d1a991b46d29c4e", "generation_seconds_batch": 16.29145611997228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014942318201065063, "target_z": -0.2832031379765373, "ce": 6.229123115539551, "genuineness": 4.457139015197754, "identity": 0.6837247610092163, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Stond hier naast de hoge boekenkast. We zetten het na de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b326f57872341bb3e1abfc21a29c32d1e89d47581e3d55d9478933f1837feb52.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "b34097e9eea52c2743603dc104637af1315bc97ff6813dd42316c8c5d6341344", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e7141b69bcc93f9c4699445ed3d822736e9fac64d1a7d24e138621e4aacf01d0", "generation_seconds_batch": 28.10403846995905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054051220417022705, "target_z": -0.21289062625579394, "ce": 6.086154937744141, "genuineness": 4.325342178344727, "identity": 0.6159478425979614, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b34097e9eea52c2743603dc104637af1315bc97ff6813dd42316c8c5d6341344.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "b34dc7995295bf9e09b73abbaaa6b9ec8eb8f5c77e2974bec2b8c5cd341eebb2", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f63cf6b5559c061782ac2f25d9f094829d8ca90e2818ca848a2ded5906a851c5", "generation_seconds_batch": 22.693872364936396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08881468325853348, "target_z": -0.15039062625579394, "ce": 6.046441555023193, "genuineness": 4.545003414154053, "identity": 0.6288408041000366, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/b34dc7995295bf9e09b73abbaaa6b9ec8eb8f5c77e2974bec2b8c5cd341eebb2.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "b37e39e146d17238ae466449729c5102aaf61393515e98d3a5113aae6d862ba4", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "dc92f7303f25429bdac7a8d64a690ee944740f2078ba3b437c73dcb28529e7b0", "generation_seconds_batch": 23.90098298189696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014942318201065063, "target_z": -0.2832031379765373, "ce": 6.038498878479004, "genuineness": 4.494794845581055, "identity": 0.7127482891082764, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/b37e39e146d17238ae466449729c5102aaf61393515e98d3a5113aae6d862ba4.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "dc60564872ff6c8d0e1bf873432c1c45d6d39dc7a0ee881aa10b08bd6ac22e56", "generation_seconds_batch": 17.993259836919606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009510532021522522, "target_z": -0.2929687541859798, "ce": 6.332377910614014, "genuineness": 4.331617832183838, "identity": 0.5750288963317871, "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_Intoxication_Altered_States_of_Consciousness/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "b438b126a94058ff07b85c851525e52dc63a4fc58bed1c4c64d4dd9060a3ea7a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "50b39d59b7bb64df2329dabd81a6e8ea02717cec04670ee57ff5e3ab6503faf2", "generation_seconds_batch": 17.00764268299099, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2550274729728699, "target_z": 0.14843746818655373, "ce": 5.855817794799805, "genuineness": 4.381826400756836, "identity": 0.6697090864181519, "hypothesis": "Ik heb een kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b438b126a94058ff07b85c851525e52dc63a4fc58bed1c4c64d4dd9060a3ea7a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "b58cf2e38fcc3167128b15645b0c659c668f0145a35cdb15235030bea7f73f30", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "90743c4324bc795380e4362beaf0ea96ce7d1bb12d4b7a55a7cbcea3dbbd8ec2", "generation_seconds_batch": 23.228618724970147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05622393637895584, "target_z": -0.2089843770929899, "ce": 6.054384231567383, "genuineness": 4.482243061065674, "identity": 0.5949106812477112, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/b58cf2e38fcc3167128b15645b0c659c668f0145a35cdb15235030bea7f73f30.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "b5a6b7bf8e588d836e1bfadd624d12ed0fbfb639ebe6287ac1872ffd7c4d9ed1", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "84d547781bd48251dc88212aa93625934b2aca445eb6a6222768487afeb680ff", "generation_seconds_batch": 24.108649909030646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002992391586303711, "target_z": -0.3046874882792566, "ce": 5.879645347595215, "genuineness": 4.7332844734191895, "identity": 0.556215763092041, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b5a6b7bf8e588d836e1bfadd624d12ed0fbfb639ebe6287ac1872ffd7c4d9ed1.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "b5cfdac502462209973d068bc715d9fc918e682e36dcad278b2d1ce8cb3b134c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "01ab730105daebc8963fe0c37c5bc6db0ff271f5773b3ae748565c29acad1ae3", "generation_seconds_batch": 25.378147062961943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033410415053367615, "target_z": -0.25, "ce": 5.959072113037109, "genuineness": 4.21237325668335, "identity": 0.6258738040924072, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b5cfdac502462209973d068bc715d9fc918e682e36dcad278b2d1ce8cb3b134c.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": "b624881c6684b10391dfe51d77d01fcb3cb45fc966f3c3b6fbe8f009947c1563", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "021af0b26bb56f3831721ceb08a71e086694b169cb8b3f9307ae2bb92dc69b0f", "generation_seconds_batch": 19.444371746038087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01547570526599884, "target_z": -0.3378906262557939, "ce": 5.677107334136963, "genuineness": 4.65797233581543, "identity": 0.7443414926528931, "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_Intoxication_Altered_States_of_Consciousness/b624881c6684b10391dfe51d77d01fcb3cb45fc966f3c3b6fbe8f009947c1563.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "b67cd75411c8240eb368359ceddc4d2962f68f1e4dae0704b8fb360965734fe9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b0f244a88b317ee00196fd900a4da8d8e6e99ecfd97d9581713f79444b0cd7d8", "generation_seconds_batch": 25.299864131957293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008957549929618835, "target_z": -0.3261718653722465, "ce": 6.149696350097656, "genuineness": 4.595211505889893, "identity": 0.6145429015159607, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b67cd75411c8240eb368359ceddc4d2962f68f1e4dae0704b8fb360965734fe9.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "b6a86abd38353acbb089b2acd495669327bb407531ba793d206ac563262ad998", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b502c4865dae0de1131e2bc00524df1e982c3e02c9f24ef845e7e3cfda34aa71", "generation_seconds_batch": 24.012058028019965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05024896562099457, "target_z": -0.21972656563948484, "ce": 6.23706579208374, "genuineness": 4.557555198669434, "identity": 0.6939552426338196, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b6a86abd38353acbb089b2acd495669327bb407531ba793d206ac563262ad998.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "b72bc41f5a3bb4330ca60318b7ff2035b0040b39d2416d86b95be3ee633c94a2", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9b6d4977c160850c4101e4bc20363530ef08f7e732bd2cb59d56c1a4872bcca5", "generation_seconds_batch": 24.29743661696557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009510532021522522, "target_z": -0.2929687541859798, "ce": 6.062326908111572, "genuineness": 4.557555198669434, "identity": 0.6735689043998718, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/b72bc41f5a3bb4330ca60318b7ff2035b0040b39d2416d86b95be3ee633c94a2.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "b74724daeb37a83fb7ed7fee746189ca3d54c89df57cecae3a11ca1d92593984", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "eae2fe1792fa6ba2f384da140b7e69e006ecd803ee55685b054978e87c0f36b0", "generation_seconds_batch": 22.808710046927445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010596886277198792, "target_z": -0.2910156363021454, "ce": 6.165581703186035, "genuineness": 4.300237655639648, "identity": 0.3830159306526184, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b74724daeb37a83fb7ed7fee746189ca3d54c89df57cecae3a11ca1d92593984.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": "b793d7dafe56a7e908f9dabf953b5673bbf216029d9909b15563125624caceda", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "2150cf62b701561034b04c76b5bcbb1cb15252ad9091927fe8c19d02b0b7d47d", "generation_seconds_batch": 17.424085525097325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03992857038974762, "target_z": -0.2382812391164526, "ce": 5.689021587371826, "genuineness": 4.645420074462891, "identity": 0.633906364440918, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b793d7dafe56a7e908f9dabf953b5673bbf216029d9909b15563125624caceda.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "b8ef32d52ef549b0a936ac9ed87a325426550129bd0238dd9478485b117542ff", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "744c79126106a54a1eb6c3f50bd7a1811ada05f85a1e764d60a9ea370b61e865", "generation_seconds_batch": 18.155946778017096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 5.756534099578857, "genuineness": 4.8588056564331055, "identity": 0.6899745464324951, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b8ef32d52ef549b0a936ac9ed87a325426550129bd0238dd9478485b117542ff.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "b8fe14fff1edd81261e3aae46a053c0058fdfcb8f3ef407c2eb53806cf439401", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "418e8e7f31c3c7a941dd8f5a0c85f5ec7d8b60c16136b10cf07d77f505c93933", "generation_seconds_batch": 18.155946778017096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.044817179441452026, "target_z": -0.2294921818489273, "ce": 6.062326908111572, "genuineness": 4.833701133728027, "identity": 0.49202820658683777, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b8fe14fff1edd81261e3aae46a053c0058fdfcb8f3ef407c2eb53806cf439401.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": "b958a53f14096afd8707bfb6e0c06fd26fe1e94cb84108b8a694e4a86027d5b2", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d5e8cb7d7614bdf399b74b93c0c6c25fa42b01e6e7aeeccc0b38771daf6b6ae9", "generation_seconds_batch": 24.146354010910727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011683255434036255, "target_z": -0.28906249162804043, "ce": 5.935244083404541, "genuineness": 4.808597087860107, "identity": 0.8606841564178467, "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_Intoxication_Altered_States_of_Consciousness/b958a53f14096afd8707bfb6e0c06fd26fe1e94cb84108b8a694e4a86027d5b2.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "b972ef0c3de6e9210a49607b31d905714966be6f6c56137e41c202025302abd0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bc0f47a2fe841959fd5b566f38bd17f62720c5319ae77b157885ef10e09f4655", "generation_seconds_batch": 27.485168176004663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0507921427488327, "target_z": -0.21875000669756764, "ce": 5.990842819213867, "genuineness": 4.65797233581543, "identity": 0.4454880356788635, "hypothesis": "Die Tür 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_Intoxication_Altered_States_of_Consciousness/b972ef0c3de6e9210a49607b31d905714966be6f6c56137e41c202025302abd0.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "b975cba72a69b9ae6100a89ce6bf98cfb3418dd61954453e0ea4c4cc15e19431", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "55a66134bea6dee27882c32575f125cd35cf7708a566e507e3076f197a3da8fd", "generation_seconds_batch": 30.109883110038936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0236331969499588, "target_z": -0.2675781145350506, "ce": 6.109982967376709, "genuineness": 4.061748504638672, "identity": 0.35682180523872375, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b975cba72a69b9ae6100a89ce6bf98cfb3418dd61954453e0ea4c4cc15e19431.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": "b9dd6d526329c27ba200fb710a4bfd32fc54a8ab4a41836bde564f8d5c70dab0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "08361a48a397a6dc8cba204e314b62672ac1c1a3fc436cc09bd593bea84926d5", "generation_seconds_batch": 18.361891373060644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2680637836456299, "target_z": 0.17187498995364855, "ce": 5.974957466125488, "genuineness": 4.331617832183838, "identity": 0.6392236948013306, "hypothesis": "Ik schrijf het nummer of de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/b9dd6d526329c27ba200fb710a4bfd32fc54a8ab4a41836bde564f8d5c70dab0.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "62b611d9d7ee647cf951280efce2963b42132b717a8cfd32d819fe8d186cf4da", "generation_seconds_batch": 17.439405690063722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.010043919086456299, "target_z": -0.3281250100463515, "ce": 6.300607204437256, "genuineness": 4.720732688903809, "identity": 0.7519089579582214, "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_Intoxication_Altered_States_of_Consciousness/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.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": "ba9c8576a8cef984106dafe9c1d9ce42824293d798370def15eeb9393bd50010", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "2d4bd7968dcf135864a0324dfaa586746d6dc8b9eec03f2b0da0b59d6068bbc5", "generation_seconds_batch": 20.099103939021006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2648047208786011, "target_z": 0.1660156363021454, "ce": 5.863759994506836, "genuineness": 4.268857479095459, "identity": 0.29688477516174316, "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_Intoxication_Altered_States_of_Consciousness/ba9c8576a8cef984106dafe9c1d9ce42824293d798370def15eeb9393bd50010.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "ba9f4dda047a8002d38f406425b6aa023f06ca75388f51910402e794e43f46b5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "df4b5c556435f01ef2515e8af51d56ea07f4631107223d0fbc2b8f413a11652b", "generation_seconds_batch": 23.5650017329026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1551504284143448, "target_z": -0.031127936829827986, "ce": 6.125868320465088, "genuineness": 4.532451152801514, "identity": 0.6007851362228394, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/ba9f4dda047a8002d38f406425b6aa023f06ca75388f51910402e794e43f46b5.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "bb5d3c1fb54f6ba9ae603d6b5ef1ef74d319edfa4fa197694d69f19e4120b8e6", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f409465b9c53cf5597a61721fbdd3a673fe80037132967f0015725ce866edbc2", "generation_seconds_batch": 19.270495526026934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.23706579208374, "genuineness": 4.595211505889893, "identity": 0.5275604724884033, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/bb5d3c1fb54f6ba9ae603d6b5ef1ef74d319edfa4fa197694d69f19e4120b8e6.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": "bb7288d053b640335a8bda81375f2211911110170024bc0655ae69ead7c098d4", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d0c5b0356936f31f732a69ff570b674a853bb97bce5b01aa8d9e9e492d11968d", "generation_seconds_batch": 29.741492870030925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.038842201232910156, "target_z": -0.24023438379055753, "ce": 6.046441555023193, "genuineness": 4.369274139404297, "identity": 0.6424251794815063, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/bb7288d053b640335a8bda81375f2211911110170024bc0655ae69ead7c098d4.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "bb9415b16f1cc7b941433ac8f3754ea57cc72a41e408d55cbec1e66eb084c453", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "871073eb21e3058e1f45871f8dcee6d7222ff83594cc573e2aee3f3d31fb5e4f", "generation_seconds_batch": 23.487585082068108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054051220417022705, "target_z": -0.21289062625579394, "ce": 5.959072113037109, "genuineness": 4.582659721374512, "identity": 0.4745379388332367, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/bb9415b16f1cc7b941433ac8f3754ea57cc72a41e408d55cbec1e66eb084c453.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "bb9475d1c2567d1da584eadb8d900b055a294151339ac2eb4139bdc1d1f11d4a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1f7ecf028018830ddcdfe4834874a0bd7f762a5fd1a5f10fff0843f93ee35a5a", "generation_seconds_batch": 16.940183316008188, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03775584697723389, "target_z": -0.2421875016743919, "ce": 6.157639026641846, "genuineness": 4.68307638168335, "identity": 0.4884074628353119, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/bb9475d1c2567d1da584eadb8d900b055a294151339ac2eb4139bdc1d1f11d4a.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": "bbc946517c84d975255d1d65e77537a8bd921edf801e18043e4c2634729689f4", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "3edaabbd8767798b4d6c2f92b3c7244d15f72021f777e25f7002f68a4d600174", "generation_seconds_batch": 16.324027789989486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0236331969499588, "target_z": -0.2675781145350506, "ce": 6.23706579208374, "genuineness": 4.582659721374512, "identity": 0.4391542673110962, "hypothesis": "Someone moved the little blue chair. It used to stand here beside the tall bookshelf. We can put it back after lunch.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/bbc946517c84d975255d1d65e77537a8bd921edf801e18043e4c2634729689f4.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "bc75e80083b5019d7a276208915641563d225746321164b92882ed6445a3a978", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "7f800795b14b49609d657285738135c1f367df81d76d9a2081deb21c20505873", "generation_seconds_batch": 22.468945603002794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016028687357902527, "target_z": -0.2812499933024324, "ce": 6.09409761428833, "genuineness": 4.444586753845215, "identity": 0.4438948333263397, "hypothesis": "I f found the little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/bc75e80083b5019d7a276208915641563d225746321164b92882ed6445a3a978.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "bcc6e798c619147b892f47e480b855a76e1f0b32d1415588839a581d66f46d0b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "611ca87a5e4febf455bf72405918688cf7c6e5173887f8ec00fcf572f13fe36c", "generation_seconds_batch": 17.904332706006244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030151337385177612, "target_z": -0.2558593804417737, "ce": 6.2767791748046875, "genuineness": 4.406930446624756, "identity": 0.38478970527648926, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/bcc6e798c619147b892f47e480b855a76e1f0b32d1415588839a581d66f46d0b.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": "bd2f21758f0b69d74741b3e2a51e8932cafeefde17cb8e1b44f74675ae39d69d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "7baa4fa65d1f1c29d22660022c907ddc1d685c16306c1d201a2e188d07671c20", "generation_seconds_batch": 15.979272366967052, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10701118409633636, "target_z": -0.1176757811453505, "ce": 5.824047088623047, "genuineness": 4.519899368286133, "identity": 0.47559860348701477, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/bd2f21758f0b69d74741b3e2a51e8932cafeefde17cb8e1b44f74675ae39d69d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "bd5b7e616b4fdfea6659e50acb91955be42f11a7927d1bd41a87960106eb445b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "47f7c977977d2054ab71d034b5771fad99293926b43b83f7893e58200fec5c7d", "generation_seconds_batch": 25.29367272905074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00516510009765625, "target_z": -0.3007812525115879, "ce": 6.133810997009277, "genuineness": 4.557555198669434, "identity": 0.7663441300392151, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/bd5b7e616b4fdfea6659e50acb91955be42f11a7927d1bd41a87960106eb445b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "bd6a06b08c95d9f75cb9038ecda4103aef7df810fb269b1c046dc957ec620e46", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5a45424f0231878f070a7c407cf38e392674275f1af7b1098667f127555bb0aa", "generation_seconds_batch": 22.943109089974314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030151337385177612, "target_z": -0.2558593804417737, "ce": 6.252951145172119, "genuineness": 4.65797233581543, "identity": 0.7159770131111145, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Ah", "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_Intoxication_Altered_States_of_Consciousness/bd6a06b08c95d9f75cb9038ecda4103aef7df810fb269b1c046dc957ec620e46.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "bd74f4e302445eb059738cdb2fbf936f5c78f2d16b21ed44b1ec94e8395d6d1b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "33c606be7f07f54d1eb21e193207a228f1d8fbfa12cbe68127a59b32892e89ed", "generation_seconds_batch": 22.256480418960564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010596886277198792, "target_z": -0.2910156363021454, "ce": 5.601652145385742, "genuineness": 4.2751336097717285, "identity": 0.393535315990448, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/bd74f4e302445eb059738cdb2fbf936f5c78f2d16b21ed44b1ec94e8395d6d1b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "be41d85b445f2af725d33b30c79d4bdc2c3e5f8ed60a59124c8e1f4b590fc15e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9899eac5ab03eef7f7cb86026cdf6837a1e9f3610693dd656064c87f8d5f23f1", "generation_seconds_batch": 22.853835194022395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 6.252951145172119, "genuineness": 4.65797233581543, "identity": 0.17126816511154175, "hypothesis": "I found the little box. It was beside the old w window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/be41d85b445f2af725d33b30c79d4bdc2c3e5f8ed60a59124c8e1f4b590fc15e.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": "be4706eaf61438e34326bbf7a29080a258431a402ecb2505cacd7096bb473b07", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "2dbe8b4cf411d9f4ab2c12be8ba7d12ec1059c311c9022aa3e14f3d7fa5f61d4", "generation_seconds_batch": 20.683103888994083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04861942678689957, "target_z": -0.2226562558603717, "ce": 6.157639026641846, "genuineness": 4.796044826507568, "identity": 0.8060178756713867, "hypothesis": "La route tourne à gauche après le pont. Continue jusqu'à la jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.1, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/be4706eaf61438e34326bbf7a29080a258431a402ecb2505cacd7096bb473b07.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "be65c7d99706bf7e7d90619bacba627a1b4ac0ad2d2bc47752344dabd04dda70", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78eddec44ebb99a4e8deb12e43859adb62eee382f2018e99159907997a112327", "generation_seconds_batch": 22.467835608054884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 6.086154937744141, "genuineness": 4.532451152801514, "identity": 0.6993341445922852, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/be65c7d99706bf7e7d90619bacba627a1b4ac0ad2d2bc47752344dabd04dda70.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "be984c5fb1a1e56e06432fd2da8f52313e478b7a550d7f8174f3d5b7a16979ff", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "wording", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "daf67fc00ac7eb5000151a7281703c0d6df7dd7f22dfc3e126cf8da6d6d9a2ba", "generation_seconds_batch": 17.426714544999413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 6.125868320465088, "genuineness": 4.770940780639648, "identity": 0.6737022399902344, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/be984c5fb1a1e56e06432fd2da8f52313e478b7a550d7f8174f3d5b7a16979ff.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "bf23201efe01c4c632efdb6575f406cb8fb0f8860cee9432e41449db6fe12256", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a456c369ffa0288137a960fa9315961561f7a93f2e8d2797f2e2c3c2375736cf", "generation_seconds_batch": 25.3230824500788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013855963945388794, "target_z": -0.2851562558603717, "ce": 6.0146708488464355, "genuineness": 4.607763767242432, "identity": 0.8211218118667603, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/bf23201efe01c4c632efdb6575f406cb8fb0f8860cee9432e41449db6fe12256.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "bf480f0265eab833420601fc0d170db3772cf773ef4143aeb8e542e7c57a88ba", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2ea21b8cb9273f60e4e101d76eca69849a393250d716f64579aa5a71755a66d8", "generation_seconds_batch": 18.164981956011616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04427400231361389, "target_z": -0.2304687407908445, "ce": 5.728734970092773, "genuineness": 4.7458367347717285, "identity": 0.6054665446281433, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/bf480f0265eab833420601fc0d170db3772cf773ef4143aeb8e542e7c57a88ba.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "bf730cf6c16631c714ef11e4d6556e139c2e1702c03e7b566092c24914537aa5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8b0d6e6693611376bc29f03746537d1a15d8fa99354140b6786b7b23a766be4e", "generation_seconds_batch": 25.859083062969148, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031237691640853882, "target_z": -0.2539062625579393, "ce": 6.427689552307129, "genuineness": 4.6705241203308105, "identity": 0.23443692922592163, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/bf730cf6c16631c714ef11e4d6556e139c2e1702c03e7b566092c24914537aa5.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "bf810db5ef0e9c103580e98977a7ec90fe8ce4e8ef05a6feb449ff208af18635", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "wording", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f368f8db727c9082c4db23328dc1fc0fcd6ca6df495ec29aa41838c6cfee7037", "generation_seconds_batch": 17.426714544999413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0019060224294662476, "target_z": -0.3066406329533616, "ce": 6.260893821716309, "genuineness": 4.432034492492676, "identity": 0.7267848253250122, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/bf810db5ef0e9c103580e98977a7ec90fe8ce4e8ef05a6feb449ff208af18635.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": "bfab61dff69112d9b5021de4ba3628c6c854a760e91189a361c829efde08cd97", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "459f8f1812df9c209dfc7291484b916dc49156978fbfc1fce9f9b56baf54820d", "generation_seconds_batch": 22.71209559997078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21754813194274902, "target_z": 0.08105468687210303, "ce": 5.903473377227783, "genuineness": 4.325342178344727, "identity": 0.7218263149261475, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine Houtenhek. Ik wacht ik. ik wacht aan de andere kant.", "wer": 0.23809523809523808, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/bfab61dff69112d9b5021de4ba3628c6c854a760e91189a361c829efde08cd97.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "c0497aaecc7439a81041ac58ad1ea990cac4363a31667bb97f7000eb0e2355e0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3909f6e08098706fd1336538e182dfd74571db215d95906012ad5b25d98ba3be", "generation_seconds_batch": 22.230646535987034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07034659385681152, "target_z": -0.18359375083719595, "ce": 6.054384231567383, "genuineness": 4.482243061065674, "identity": 0.6366844177246094, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/c0497aaecc7439a81041ac58ad1ea990cac4363a31667bb97f7000eb0e2355e0.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "c0cdafe58208eb8da866d5c3ed7b6bbf5df5e6dd6d0d63b053ea7e04e3554905", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "37652c5d1543626330704832b7b2df8c3ea53b0992e349c467661fb3461fd24f", "generation_seconds_batch": 23.117969604907557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 6.316492557525635, "genuineness": 4.1998209953308105, "identity": 0.5272480845451355, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/c0cdafe58208eb8da866d5c3ed7b6bbf5df5e6dd6d0d63b053ea7e04e3554905.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "c0d5ad7fa6dcaf88cd346d6447951bd332fc3c4cb1a6f4966634c2577794feab", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4050c54237da8dc1db66e477e5a10a331aaf379ccfe9f239abbb7b76db01f13b", "generation_seconds_batch": 23.515260620974004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013855963945388794, "target_z": -0.2851562558603717, "ce": 5.863759994506836, "genuineness": 4.7332844734191895, "identity": 0.6743022799491882, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/c0d5ad7fa6dcaf88cd346d6447951bd332fc3c4cb1a6f4966634c2577794feab.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "c1a66dbb825fe725b0f262b5273ff9c8e172e00e47bff0ebbd55668fb6558630", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d9fc486d218d8e086f3f8cf4ff7c6d2fa377ad547155b186a1095a3d0da3d404", "generation_seconds_batch": 24.108649909030646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002992391586303711, "target_z": -0.3046874882792566, "ce": 6.09409761428833, "genuineness": 4.7332844734191895, "identity": 0.6556389927864075, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/c1a66dbb825fe725b0f262b5273ff9c8e172e00e47bff0ebbd55668fb6558630.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": "c1e738ac91802793b762011754e2614d18583553b346f9f6cea66c3159ea8da4", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "d4f9eb79a13f1dfdf1f2a3b5cce4e5293a2eae105e8343803f4ce51f04a5118b", "generation_seconds_batch": 16.324027789989486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 6.308549880981445, "genuineness": 4.532451152801514, "identity": 0.37710070610046387, "hypothesis": "Someone moved a little blue chair. It used to stand here beside the tall bookshelf. We can put it back after lunch.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/c1e738ac91802793b762011754e2614d18583553b346f9f6cea66c3159ea8da4.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": "c270112808a49b5de585a703f18b4e09f93d926e838862b6937ba1f2ade0eb7c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "68351f4bc31a825c77e45957e7edcd2d3b4621cce5c36ca85d0eb8c7101d3c4e", "generation_seconds_batch": 20.683103888994083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0491626113653183, "target_z": -0.2216796835233192, "ce": 5.982900142669678, "genuineness": 4.65797233581543, "identity": 0.8443846106529236, "hypothesis": "La route tourne à gauche après le ponce continue jusqu'à la petite barrière en bois.", "wer": 0.3, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/c270112808a49b5de585a703f18b4e09f93d926e838862b6937ba1f2ade0eb7c.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "c2a437938fb64e6de35d606627edcab987b076edda7217228d5de7502ee89c67", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "fce432d26dc6b02568ee7c794aaaeaa5c29f80bd85ba8da4c7e8979a1d76740a", "generation_seconds_batch": 25.02730117808096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014942318201065063, "target_z": -0.2832031379765373, "ce": 5.998785495758057, "genuineness": 4.770940780639648, "identity": 0.5695942640304565, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/c2a437938fb64e6de35d606627edcab987b076edda7217228d5de7502ee89c67.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "c364c174a7ae28304d84ae879602dbb6a28f8ef3184f448599f190534c5d12d1", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e34a223014c549d2ec578681732b5ffe7a65247e289fba1d91fc471b3d6463bc", "generation_seconds_batch": 25.029561156989075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08664196729660034, "target_z": -0.154296875418598, "ce": 5.696964263916016, "genuineness": 4.482243061065674, "identity": 0.5384874939918518, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/c364c174a7ae28304d84ae879602dbb6a28f8ef3184f448599f190534c5d12d1.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "79354c108daaf1cfdecdff1170beda083d74dffa3ef66320766c8e5115684f5c", "generation_seconds_batch": 16.638545169029385, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 6.109982967376709, "genuineness": 4.632867813110352, "identity": 0.766505241394043, "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_Intoxication_Altered_States_of_Consciousness/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "c3a8f298a85596f926f7c946c0d955296fd4be82bb680cf53bd2a3a78b132797", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eb544be04be1d0dd8184740be73a855c33c1d439297689e40cfc33c1e73f9085", "generation_seconds_batch": 22.75058632402215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03558313846588135, "target_z": -0.24609373744206067, "ce": 6.316492557525635, "genuineness": 4.7458367347717285, "identity": 0.4293588101863861, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/c3a8f298a85596f926f7c946c0d955296fd4be82bb680cf53bd2a3a78b132797.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "f87333778dc10f8ebec2102728bf685f230b40ff1148e689209f0604ed6b98ed", "generation_seconds_batch": 20.397069229045883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007337823510169983, "target_z": -0.2968749899536485, "ce": 6.109982967376709, "genuineness": 4.519899368286133, "identity": 0.5841256976127625, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Dat stond hier naast de hoge boekenkast. We zetten het na de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "c4b96aeb3862586860b7bf1af4c195128e0be4db6eea1e12ac0631c267b1ea4b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "fb7d5a69679eb7216615b30f95459e700267ec499fc1393fb54794b580a47a2b", "generation_seconds_batch": 25.378147062961943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.109982967376709, "genuineness": 4.469690799713135, "identity": 0.5899599194526672, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/c4b96aeb3862586860b7bf1af4c195128e0be4db6eea1e12ac0631c267b1ea4b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "c5244446dd1b79cda75bcbee3ee86540a39026746d8a4590c8ac46d9b578b108", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5bb6ed375a45d8cf2b79a932a6637be36e6b6d9e885c38b237abd3a7ec5e1481", "generation_seconds_batch": 24.726610089070164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03612631559371948, "target_z": -0.2451171785001435, "ce": 6.38003396987915, "genuineness": 4.720732688903809, "identity": 0.4632612466812134, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/c5244446dd1b79cda75bcbee3ee86540a39026746d8a4590c8ac46d9b578b108.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "c5274151c71f1c35e70a511be7ba0bebe00b30188ae57b1b7d4a4e942c8f6ac7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b2cf85380cf5cf1ba13524894b4dd44de8819563579b4581f4bcce479c3f8f0f", "generation_seconds_batch": 26.063175354967825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04318763315677643, "target_z": -0.23242188546494943, "ce": 6.133810997009277, "genuineness": 4.65797233581543, "identity": 0.7416079044342041, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/c5274151c71f1c35e70a511be7ba0bebe00b30188ae57b1b7d4a4e942c8f6ac7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "c5e80109d6885d1a0f85c673c7b8ae49e8c522803e787fa567d559cf2545b20a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "14ed8a39d629f233e3de6e3e99674c0970699e4ab063a202f957dbd387aa8fff", "generation_seconds_batch": 23.938322264002636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7156433463096619, "target_z": 0.9765624514426346, "ce": 5.8875885009765625, "genuineness": 4.1998209953308105, "identity": 0.4245666265487671, "hypothesis": "Ik heb het kleine cadeautje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/c5e80109d6885d1a0f85c673c7b8ae49e8c522803e787fa567d559cf2545b20a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "c61ba51e7c565b6d2c8210b4ab704e5191d43734950a468d437605f61d6b2747", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "bbb231149aae15d470cfb765b117b493fdffec8bc2fb64f0f5f8f7c99d630c24", "generation_seconds_batch": 17.756876370985992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016028687357902527, "target_z": -0.2812499933024324, "ce": 6.324435234069824, "genuineness": 4.049196243286133, "identity": 0.722172737121582, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/c61ba51e7c565b6d2c8210b4ab704e5191d43734950a468d437605f61d6b2747.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": "c62644dc1a1cbf315ec69b75ddfb3c7af82d769000b8497ba4629a5fc30166b1", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5248402755b6344e18ba91dbbda507ea70aa9ee68f44914f5d390a8cac353bd8", "generation_seconds_batch": 23.374196961987764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013855963945388794, "target_z": -0.2851562558603717, "ce": 6.252951145172119, "genuineness": 4.432034492492676, "identity": 0.3242936432361603, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/c62644dc1a1cbf315ec69b75ddfb3c7af82d769000b8497ba4629a5fc30166b1.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "c669995e7d4ca76bfc65355cde486afcac2107757ba0719ad902e3c0cbf8b17a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fba51abd206efe7cfa3adde09e6e1bce17712799b51907cdad6bbb48321d69f5", "generation_seconds_batch": 23.145534039940685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2870750427246094, "target_z": 0.20605466008183249, "ce": 6.038498878479004, "genuineness": 4.482243061065674, "identity": 0.5939429402351379, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/c669995e7d4ca76bfc65355cde486afcac2107757ba0719ad902e3c0cbf8b17a.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": "c6de9c5ef76d9ceb206bb03da9614e11ad8def3e650cc8a948d1ac9133856c4f", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5f37427c3da7979f44eadefcccf426889c20f3797606aaf1856dc41195ccffeb", "generation_seconds_batch": 24.433519550948404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05459439754486084, "target_z": -0.21191406731387674, "ce": 5.6254801750183105, "genuineness": 4.582659721374512, "identity": 0.5274767875671387, "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_Intoxication_Altered_States_of_Consciousness/c6de9c5ef76d9ceb206bb03da9614e11ad8def3e650cc8a948d1ac9133856c4f.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "c6f72117593c1e5ecc465353728e46a480943377b252ce8ad0c3fae174fd206c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9e1a875108a51ddf221770609e1445b8047a56d74e2abfaa8ee6158a3ab3171e", "generation_seconds_batch": 18.40033161395695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04318763315677643, "target_z": -0.23242188546494943, "ce": 5.657250881195068, "genuineness": 4.883909225463867, "identity": 0.7239078283309937, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/c6f72117593c1e5ecc465353728e46a480943377b252ce8ad0c3fae174fd206c.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": "c7d8fd84d8d648e5415deddb094d73f85a3b1830f68deab48cd161546e80b3a1", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "16f06dcae4104260a2b808325c54652ab4849531fae8ce605d88925f5d3070fe", "generation_seconds_batch": 18.343291722936556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03558313846588135, "target_z": -0.24609373744206067, "ce": 6.062326908111572, "genuineness": 4.2751336097717285, "identity": 0.5425203442573547, "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_Intoxication_Altered_States_of_Consciousness/c7d8fd84d8d648e5415deddb094d73f85a3b1830f68deab48cd161546e80b3a1.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "140ae530e040180370545d5cef6c9efad758656d3927d530962b1d86917ebdce", "generation_seconds_batch": 16.667439923039638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02689225971698761, "target_z": -0.2617187608835474, "ce": 6.316492557525635, "genuineness": 4.482243061065674, "identity": 0.5840394496917725, "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_Intoxication_Altered_States_of_Consciousness/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "c87559f532613139a83e2871509d07ecb4942e44fc1315ee61e128985e70e64a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "wording", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "685dd9bfdf732712ab398f1e6f4e5d5e3adfb7f40cf1dbb45a02731c95422be9", "generation_seconds_batch": 17.193721253075637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04264445602893829, "target_z": -0.23339844440686663, "ce": 6.268836498260498, "genuineness": 4.582659721374512, "identity": 0.5333231687545776, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/c87559f532613139a83e2871509d07ecb4942e44fc1315ee61e128985e70e64a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "c88dceef340655e1b1d773ef86031b603ce554f1bf81f8c6fb0f75d8dfa533af", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5bc5b7763d1df361496c42abf7c213a367555b89a6ff5da37d3ef7af7dd67075", "generation_seconds_batch": 22.868231364060193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031237691640853882, "target_z": -0.2539062625579393, "ce": 6.165581703186035, "genuineness": 4.720732688903809, "identity": 0.7414382696151733, "hypothesis": "La porte est encore ouverte. J'ai j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/c88dceef340655e1b1d773ef86031b603ce554f1bf81f8c6fb0f75d8dfa533af.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "26b70c8678085815b438ef4944d52a27d10b888cfc4fb6efadaea0766dcfe3e4", "generation_seconds_batch": 18.585244117071852, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 6.53094482421875, "genuineness": 4.557555198669434, "identity": 0.2820149064064026, "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_Intoxication_Altered_States_of_Consciousness/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "c8c170a623c286884d78a63f0bda5b7cb6f8b9691e1c9d58f1b8b9fa757f22ac", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0943f3e30b92864d22a6198178fd2a3f8e76e1e2de8e6b83ddd366b280d71ce5", "generation_seconds_batch": 24.886785384034738, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.1020402908325195, "genuineness": 4.7081804275512695, "identity": 0.6436219215393066, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/c8c170a623c286884d78a63f0bda5b7cb6f8b9691e1c9d58f1b8b9fa757f22ac.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "c8e5118fee119baac20cba323edbef65e5ade0ae0d7431566cab64d942abb612", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc6f7e32b517a87944048f94ca577ff9223a1eb9cd90d879a3817030804acf7b", "generation_seconds_batch": 21.952454853919335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030151337385177612, "target_z": -0.2558593804417737, "ce": 6.395919322967529, "genuineness": 4.507347106933594, "identity": 0.6080383658409119, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/c8e5118fee119baac20cba323edbef65e5ade0ae0d7431566cab64d942abb612.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "c94ebec380aa7ef3df708b25a6cc2d0fb2b5e00e733ed5ec70da03dc86161f26", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c2ed51e018bdb09d6a67d755b6084ffa8fc6a4da586b0468627e8c74a68de54f", "generation_seconds_batch": 26.70265517104417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031237691640853882, "target_z": -0.2539062625579393, "ce": 6.09409761428833, "genuineness": 4.293961524963379, "identity": 0.5679531693458557, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/c94ebec380aa7ef3df708b25a6cc2d0fb2b5e00e733ed5ec70da03dc86161f26.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": "ca33a7093ca7f35215c1e3c841fabb94c86be4ec5e6ec11d47931ac05005bb74", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "354ac5ba27c23c88b0bf9bc383fd6c2fbab343fe1c6fbb802f8a0cb7f1eeb95c", "generation_seconds_batch": 25.609408512013033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 5.998785495758057, "genuineness": 4.7332844734191895, "identity": 0.650983989238739, "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_Intoxication_Altered_States_of_Consciousness/ca33a7093ca7f35215c1e3c841fabb94c86be4ec5e6ec11d47931ac05005bb74.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "cacc56f338c1557211b800afd1af2b4da7c926e308096be997dd7b814b4fbf19", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "665673b262f2f63beff2167bc3edc9d0442c57608319fd4a2e5a5ab4a31cddb5", "generation_seconds_batch": 23.370806023012847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 6.316492557525635, "genuineness": 4.7332844734191895, "identity": 0.42124494910240173, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/cacc56f338c1557211b800afd1af2b4da7c926e308096be997dd7b814b4fbf19.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": "caf1069efaa4355482725f49524e550a646dd32ac63335b565670897e6fdd1d7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0e548668b849d338320b8de052d30177cdd738756033d05fd857427a839bc32d", "generation_seconds_batch": 23.157490471028723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 5.792276382446289, "genuineness": 4.494794845581055, "identity": 0.5578372478485107, "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_Intoxication_Altered_States_of_Consciousness/caf1069efaa4355482725f49524e550a646dd32ac63335b565670897e6fdd1d7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "cb7cd00117d71860b84001981a4058eff05decff055fe0b36e29f6f66d42705d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8dcdfa0de6b6be2c34b017ee4e2ed0f4ba210478b0361c099e266c4b6b8217ba", "generation_seconds_batch": 22.75058632402215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031237691640853882, "target_z": -0.2539062625579393, "ce": 6.1894097328186035, "genuineness": 4.507347106933594, "identity": 0.2304946929216385, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/cb7cd00117d71860b84001981a4058eff05decff055fe0b36e29f6f66d42705d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "cbce13e8f7cb57669d361e34862d1893b94b952eb56af503ddfb9bf658f90cb9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "79d873f702e85702376f9832f818ba5079e34df9c54b8bb8a4373f6ece3cec2c", "generation_seconds_batch": 24.02929765393492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02146047353744507, "target_z": -0.2714843770929899, "ce": 6.197352409362793, "genuineness": 4.331617832183838, "identity": 0.3638269007205963, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/cbce13e8f7cb57669d361e34862d1893b94b952eb56af503ddfb9bf658f90cb9.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "cc65c80a9a700522be2e5c21e5239d1965ecbd2b2127b08ecb0baf586c52d9a0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "aecc570cdcc08395a1df111b46500ae300a89f3844b120f9589771b9e7e92167", "generation_seconds_batch": 25.23569438594859, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04644671082496643, "target_z": -0.22656250502317574, "ce": 5.967014789581299, "genuineness": 4.607763767242432, "identity": 0.08112771064043045, "hypothesis": "De deur staat nog open. Ik heb je een jas op de stoel gelegd, zeg maar, wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/cc65c80a9a700522be2e5c21e5239d1965ecbd2b2127b08ecb0baf586c52d9a0.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "cd1129e744d2977e32cc3a6d070299ff611345938b383a00dc15cbf1b12eb99d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "79a5f33a29f37a7e647bf1a3d84fb9818eff5b1cf511f9f2f1797fd53dcdfc96", "generation_seconds_batch": 22.847749138018116, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016028687357902527, "target_z": -0.2812499933024324, "ce": 6.141753673553467, "genuineness": 4.15588903427124, "identity": 0.18599121272563934, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/cd1129e744d2977e32cc3a6d070299ff611345938b383a00dc15cbf1b12eb99d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "cda6e82aa3e4eb4bd4164df80eca52bfc6067169620dd945521bc07311899ec4", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "daeae37bcf617c57356f34a2e46e0b2aca012da4bee92ce8a914ac5484320c82", "generation_seconds_batch": 23.934758019982837, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07740792632102966, "target_z": -0.17089843101173136, "ce": 6.1020402908325195, "genuineness": 4.293961524963379, "identity": 0.6769559383392334, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/cda6e82aa3e4eb4bd4164df80eca52bfc6067169620dd945521bc07311899ec4.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "cdcde7cddc388a3f6e98bbd071b66fa485b1d5e4ba3bd6c5fec9938c219fc498", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "29776748f00aace8a5beaefef23e7767fc93d31aab490b37405116b0ee5e5ae8", "generation_seconds_batch": 24.584105025976896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009510532021522522, "target_z": -0.2929687541859798, "ce": 6.197352409362793, "genuineness": 4.425758361816406, "identity": 0.4229544401168823, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/cdcde7cddc388a3f6e98bbd071b66fa485b1d5e4ba3bd6c5fec9938c219fc498.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "ce8efdfafc294c110fd155e11b10ff9a5878f4c26386da2e2e5d012866fdc9fd", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd5575bbf985af050849f2f71e18a005cee55322d5df270181e185406d51eed1", "generation_seconds_batch": 23.736711986013688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013855963945388794, "target_z": -0.2851562558603717, "ce": 6.197352409362793, "genuineness": 4.770940780639648, "identity": 0.6212314367294312, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/ce8efdfafc294c110fd155e11b10ff9a5878f4c26386da2e2e5d012866fdc9fd.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "cea0bbfd59583b0a4f08d9c5ec9ce351140a9eebdb20edea8259aefbc4fa95d0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "66a20ae26fcd7dbeec946b6ef2285923244f74f94b6476c3900425b7beb7edd1", "generation_seconds_batch": 23.18378317297902, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.019821137189865112, "target_z": -0.345703124581402, "ce": 6.260893821716309, "genuineness": 4.369274139404297, "identity": 0.45173710584640503, "hypothesis": "Jemst de eerste hek, dat hond. Ik heb het kleine doosje gevonden. Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen.", "wer": 0.7777777777777778, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/cea0bbfd59583b0a4f08d9c5ec9ce351140a9eebdb20edea8259aefbc4fa95d0.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": "cee3ac8df3027631d15c2842a0a96cd0ed10647dff3fc280d9541194c2f2c522", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "2e9cad697ccb588806eeda8af894b26f5751db14b0bc5e52042223b57c47d289", "generation_seconds_batch": 18.73995905998163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04861942678689957, "target_z": -0.2226562558603717, "ce": 6.109982967376709, "genuineness": 4.68307638168335, "identity": 0.6153610348701477, "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_Intoxication_Altered_States_of_Consciousness/cee3ac8df3027631d15c2842a0a96cd0ed10647dff3fc280d9541194c2f2c522.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "cef85fcfeb0261dda2e9fdc546775ef8e9c17762441144754d25b596f1655ff0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b0f0480e7d2c229118c5acfb355016320bcb29f96d817470f99a541337559817", "generation_seconds_batch": 24.360485407989472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030151337385177612, "target_z": -0.2558593804417737, "ce": 6.300607204437256, "genuineness": 4.557555198669434, "identity": 0.5134711265563965, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/cef85fcfeb0261dda2e9fdc546775ef8e9c17762441144754d25b596f1655ff0.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": "cf1fd1150d52212c4f5116a6e8c50e50c3deb8131baa68a7f9a32aed914c1d3e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6251c35d339ffccc9b4d09f645fbd7a9952f4c90daf5081e4b2dac2e7061ad75", "generation_seconds_batch": 15.795298348995857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02580590546131134, "target_z": -0.2636718787673818, "ce": 6.141753673553467, "genuineness": 4.595211505889893, "identity": 0.6883881688117981, "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_Intoxication_Altered_States_of_Consciousness/cf1fd1150d52212c4f5116a6e8c50e50c3deb8131baa68a7f9a32aed914c1d3e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "cf2f57984da3b921cd5120c9aa260ed0969d2a42de3d65df989c8c8876611fa3", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d56a00506f06b8ef9f0f26341884c6f0f05374deafbe51897fe0efcdb4157b5a", "generation_seconds_batch": 26.7967649360653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12194861471652985, "target_z": -0.09082030308154551, "ce": 6.181467056274414, "genuineness": 4.356721878051758, "identity": 0.6145319938659668, "hypothesis": "Ja, ik heb het kleine 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_Intoxication_Altered_States_of_Consciousness/cf2f57984da3b921cd5120c9aa260ed0969d2a42de3d65df989c8c8876611fa3.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "cc49555d4f66b8dbf9a9e08a9c8b53440ee03a014658dec1119631a27b2dfbeb", "generation_seconds_batch": 16.947307890979573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04536035656929016, "target_z": -0.2285156229070101, "ce": 6.419747352600098, "genuineness": 4.425758361816406, "identity": 0.6045498847961426, "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_Intoxication_Altered_States_of_Consciousness/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "cfd5e93feb48aca07d399784e2a1372c91930423218bb8ff0303884413b597ef", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fac58658649e2cf034f0c619c7b0107c94ea33cc93652d95ab69b45c896ab800", "generation_seconds_batch": 24.657100228010677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.038842201232910156, "target_z": -0.24023438379055753, "ce": 6.300607204437256, "genuineness": 4.507347106933594, "identity": 0.5392031669616699, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/cfd5e93feb48aca07d399784e2a1372c91930423218bb8ff0303884413b597ef.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "d092c24abfbc0ad7dcbdb71b5947add808db62228a38aaa272513d4ae7224374", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2486b878da264e633431757ec7d77eb001968816b72a3daccbc6f275de220e03", "generation_seconds_batch": 24.885890766978264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06491480022668839, "target_z": -0.1933593804417737, "ce": 5.935244083404541, "genuineness": 4.281409740447998, "identity": 0.47869235277175903, "hypothesis": "De deur staat nog open. Ik heb je jas op dit stoel gelegd, zeg maar, wanneer je je klaar bent.", "wer": 0.10526315789473684, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d092c24abfbc0ad7dcbdb71b5947add808db62228a38aaa272513d4ae7224374.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": "d0f209381bd74b0acdb7aec5b45434b7bbde3048278f8426187da36b438364f8", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2933be54de2563f515f3b441d2475966888a44bca16734a8552db83c5e09979c", "generation_seconds_batch": 17.665401145000942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03829902410507202, "target_z": -0.2412109427324747, "ce": 6.1894097328186035, "genuineness": 4.6203155517578125, "identity": 0.3072681427001953, "hypothesis": "I wrote the number uh on the envelope. Read it carefully, and check the last two digits. Call me when you have a moment.", "wer": 0.043478260869565216, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d0f209381bd74b0acdb7aec5b45434b7bbde3048278f8426187da36b438364f8.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "d0fb803f32d537c92a839a8d9dd29b59942f3be4f22f0220d05d42798ec8ea37", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "65cf137cda9516ce0b0ab4465ec8e999de0d39ac4dfcac0f32d36a32e978a1ee", "generation_seconds_batch": 28.14766024996061, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054051220417022705, "target_z": -0.21289062625579394, "ce": 6.109982967376709, "genuineness": 4.494794845581055, "identity": 0.5205276012420654, "hypothesis": "I found the little box. It was beside the old window. We can l look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d0fb803f32d537c92a839a8d9dd29b59942f3be4f22f0220d05d42798ec8ea37.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "57a79e7a8f064c08645d92ee8b10079a3749d33b6f7e19a706dfc40ab99ccd58", "generation_seconds_batch": 19.38186053710524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002992391586303711, "target_z": -0.3046874882792566, "ce": 6.292664527893066, "genuineness": 3.873466968536377, "identity": 0.3906201720237732, "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_Intoxication_Altered_States_of_Consciousness/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.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": "d14174c05e6f22bbb788dd85d20e1e0353fc79bdc9e2c501861250797226ca79", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9686b4bd79aa3faca0f220587cf347cf63411cc699ee7b4aa22f5c90cf412954", "generation_seconds_batch": 22.41409624903463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6743617653846741, "target_z": 0.9023437575347636, "ce": 5.796247482299805, "genuineness": 4.469690799713135, "identity": 0.35616108775138855, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de l en daarna naast het raam Neem ze mee, als je weggaat.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d14174c05e6f22bbb788dd85d20e1e0353fc79bdc9e2c501861250797226ca79.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": "d14e7ebfb8ef86e033d87c6da0d7d034122a575f5605b943ebf6b428b39d7e07", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "873b5575fd20370158334b3bc87ce1c594e7cd67475b68b1a60b9834375bf820", "generation_seconds_batch": 26.232262989040464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09098739922046661, "target_z": -0.1464843770929899, "ce": 5.526196479797363, "genuineness": 4.7081804275512695, "identity": 0.713787317276001, "hypothesis": "J'ai écrit nos numéros sur l'enveloppe. Lis-le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d14e7ebfb8ef86e033d87c6da0d7d034122a575f5605b943ebf6b428b39d7e07.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "d190300cced5b0db0134da2d86c26a7bedb0b24cebb7025de9fdc56c38e925fc", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c2b0ec1696628153f61f344289c63cf7c952471b9f1f3ff79ecb72d98269b8fa", "generation_seconds_batch": 22.5388700759504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04373082518577576, "target_z": -0.2314452997327617, "ce": 5.6254801750183105, "genuineness": 4.796044826507568, "identity": 0.7145414352416992, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d190300cced5b0db0134da2d86c26a7bedb0b24cebb7025de9fdc56c38e925fc.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "d19e70c5a27428313d6da6d2ada853bc4d4a01698cb288248d33e704b53bcd75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "321ba0b76be9f6c9cc026965bd07e81a1b70fe2a102073f29cb2c85fc6b7ebd9", "generation_seconds_batch": 24.24674790503923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013855963945388794, "target_z": -0.2851562558603717, "ce": 6.149696350097656, "genuineness": 4.68307638168335, "identity": 0.7032086849212646, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/d19e70c5a27428313d6da6d2ada853bc4d4a01698cb288248d33e704b53bcd75.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": "d1af5a2dde22ec952b49a195c44e36e7402f7accd824257ababaf64def1c2114", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fccdbe32d465afd2f6d06739daf67c213684c9bbca16530ff85204b18c7aafcb", "generation_seconds_batch": 24.867930168984458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03666949272155762, "target_z": -0.2441406195582263, "ce": 6.133810997009277, "genuineness": 4.632867813110352, "identity": 0.6699267029762268, "hypothesis": "Ich schrieb die Nummer auf auf den Umschlag, lies sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d1af5a2dde22ec952b49a195c44e36e7402f7accd824257ababaf64def1c2114.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "d1c60cb5deb75b885e56046a57e7881d0280c705184a0512419747f162bbe185", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e4ecd1f30b88ad689b4267dab1ffb5a349ad5e3f18487eab1091305edcb397e9", "generation_seconds_batch": 22.107437659986317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012769609689712524, "target_z": -0.2871093737442061, "ce": 6.125868320465088, "genuineness": 3.973883628845215, "identity": 0.11214065551757812, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d1c60cb5deb75b885e56046a57e7881d0280c705184a0512419747f162bbe185.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "d1d76bf346eaeec30483388cb78919ec9d162716ec4333cc277ff964b317b877", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "27126f6f75562c4632c9c8ea2762bcc7ed7d72ec5e4614420b8ccff7bf718f99", "generation_seconds_batch": 17.354834969039075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02580590546131134, "target_z": -0.2636718787673818, "ce": 6.1894097328186035, "genuineness": 4.545003414154053, "identity": 0.5051952600479126, "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_Intoxication_Altered_States_of_Consciousness/d1d76bf346eaeec30483388cb78919ec9d162716ec4333cc277ff964b317b877.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "d1fd09c4c8b4080353b3f26fc23a3eab591d177f062f1a667f976f7b453c6c89", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3abb5722eb9407df5a2abb04efe2003837058ea763719f892d64e58dad48be47", "generation_seconds_batch": 25.45972253207583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017115041613578796, "target_z": -0.279296875418598, "ce": 6.3641486167907715, "genuineness": 4.519899368286133, "identity": 0.5094941258430481, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d1fd09c4c8b4080353b3f26fc23a3eab591d177f062f1a667f976f7b453c6c89.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "2e3682e0f7793e072d2d067a9adc5b2d1bcf361a783909bf8dceafe3b4b6db23", "generation_seconds_batch": 17.768031429033726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0236331969499588, "target_z": -0.2675781145350506, "ce": 6.252951145172119, "genuineness": 4.218649387359619, "identity": 0.7658518552780151, "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_Intoxication_Altered_States_of_Consciousness/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": "d2ee30d4e7b85e9a29b56c4aa823126eb9b509a2d8ee84bd2b950a8e4b389b41", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "1a8bb59a352a23f9e4a83cc0ef99cb119e2da08b29ef0a3da36958bcc673e3e8", "generation_seconds_batch": 17.66118654201273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016028687357902527, "target_z": -0.2812499933024324, "ce": 5.919358730316162, "genuineness": 4.6705241203308105, "identity": 0.6753568053245544, "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_Intoxication_Altered_States_of_Consciousness/d2ee30d4e7b85e9a29b56c4aa823126eb9b509a2d8ee84bd2b950a8e4b389b41.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "d2f9dbda6440c6c1a87212f5ca679def1cd9876923efcb8803d9739a6008e1df", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "wording", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "efd631c4b6c8b8200758aa38bfa10cfec4f045f5facb26f37a291f53f3c3f6f1", "generation_seconds_batch": 17.4195655049989, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.070269584655762, "genuineness": 4.770940780639648, "identity": 0.7002362012863159, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d2f9dbda6440c6c1a87212f5ca679def1cd9876923efcb8803d9739a6008e1df.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "d3034eaf2d8da1a6ef95b8b8324886628e7f529b86ea53abb200f95ef405e79b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8bf2d410727f8af2ad3118c26290a4809fd5e4393719a91d2b445a602d728cfd", "generation_seconds_batch": 23.179909385042265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00516510009765625, "target_z": -0.3007812525115879, "ce": 6.157639026641846, "genuineness": 4.6203155517578125, "identity": 0.5703834295272827, "hypothesis": "I found the l little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d3034eaf2d8da1a6ef95b8b8324886628e7f529b86ea53abb200f95ef405e79b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "d3283f4ca361da89716164d84ce0780a1172e8c0cf83638a4fd204a737262c70", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "84d1b68ee982bb2111328555c5ebfe5860e84ba5d76cfebc5b643d3f248ddeff", "generation_seconds_batch": 30.85701534303371, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002992391586303711, "target_z": -0.3046874882792566, "ce": 6.086154937744141, "genuineness": 4.7332844734191895, "identity": 0.5571713447570801, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d3283f4ca361da89716164d84ce0780a1172e8c0cf83638a4fd204a737262c70.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "d3b27c996f8fe6f3efbdb0ce1b8fa9083b8ecab971e2617cec57989049627cf3", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "43db0df23067f6d810eac7ac24cdaf92fbc9e5062fef985e9472c45b1c94d8c5", "generation_seconds_batch": 24.076679519028403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0507921427488327, "target_z": -0.21875000669756764, "ce": 5.863759994506836, "genuineness": 4.7332844734191895, "identity": 0.7196528315544128, "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_Intoxication_Altered_States_of_Consciousness/d3b27c996f8fe6f3efbdb0ce1b8fa9083b8ecab971e2617cec57989049627cf3.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "d3d97931ac0f92621883e77f8d36c85877a06c12b456c39bdef88b4da415b5f1", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d1b15e4d7adac53251fed43492a72cf32153394f08e93ad25fba2ae8ebc534c7", "generation_seconds_batch": 18.97511276905425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0062514543533325195, "target_z": -0.2988281346277535, "ce": 5.990842819213867, "genuineness": 4.375550270080566, "identity": 0.5886293053627014, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/d3d97931ac0f92621883e77f8d36c85877a06c12b456c39bdef88b4da415b5f1.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "f7f2a200d0ed691a9d2900e07d12326b13646a678ee405d421bb6e17a3242d24", "generation_seconds_batch": 17.799957466078922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00516510009765625, "target_z": -0.3007812525115879, "ce": 5.990842819213867, "genuineness": 4.256305694580078, "identity": 0.6114846467971802, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis-le bien et verifie 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_Intoxication_Altered_States_of_Consciousness/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "d429673dd31fe1d073c4152c64369277aa1b446dab1bb61ce5a7756dde51e07e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "83603686bca7e253f1df523cfbd38297e2317191db36f95670ecdb1118a9858f", "generation_seconds_batch": 25.40210206795018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.045903533697128296, "target_z": -0.2275390639650929, "ce": 5.824047088623047, "genuineness": 4.758388519287109, "identity": 0.5111325979232788, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d429673dd31fe1d073c4152c64369277aa1b446dab1bb61ce5a7756dde51e07e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "d47d85feca0c3e28c685b44ce6e7bf026d9076c4cc4508ab962d4ad4e50d0d69", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "21c1cf10922ca8f194b57765bd4cc3ef308a31047ddf2d63584ae54292b44806", "generation_seconds_batch": 23.270927106030285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03666949272155762, "target_z": -0.2441406195582263, "ce": 6.292664527893066, "genuineness": 4.507347106933594, "identity": 0.3846537470817566, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d47d85feca0c3e28c685b44ce6e7bf026d9076c4cc4508ab962d4ad4e50d0d69.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "d4b43448c4d1528ee0e0f275b5e8a98aef14bca310778dbb25de0b242919db1b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7221eb9cf19c1b494814979f9648c7c8e1ed3aaa6c34b9219e56083c30715d83", "generation_seconds_batch": 23.270927106030285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.229123115539551, "genuineness": 4.607763767242432, "identity": 0.45346885919570923, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d4b43448c4d1528ee0e0f275b5e8a98aef14bca310778dbb25de0b242919db1b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "d516949bec5677690c5b26e690ad993c7e81d81c25c88f43c9a496c7b34d10fc", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3c7a3b74f88f5a0a6f49bfb26d3db574cb4d34e93f276e8049607af6f622445a", "generation_seconds_batch": 23.933620670926757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02146047353744507, "target_z": -0.2714843770929899, "ce": 6.117925643920898, "genuineness": 4.469690799713135, "identity": 0.7125841379165649, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d516949bec5677690c5b26e690ad993c7e81d81c25c88f43c9a496c7b34d10fc.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "d5df1fd0f97c2d3e1a81854c2fe95bc49624ab3c2bb517d7c6d017406c9c06f2", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e76b5389d576d0a96f7f1b97f09ad03c6ffb33594a1360bef2487c3374e231ff", "generation_seconds_batch": 23.854810334043577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011683255434036255, "target_z": -0.28906249162804043, "ce": 6.054384231567383, "genuineness": 4.457139015197754, "identity": 0.5738197565078735, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d5df1fd0f97c2d3e1a81854c2fe95bc49624ab3c2bb517d7c6d017406c9c06f2.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "d5f0cef00e082e186b557e2f08b2762e41533b44c2385668fba0316a9e87f83b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "117d6792f5e87547ab92211683d82d5ba28d1df16f38718ca8f3e900f9bd3075", "generation_seconds_batch": 24.02929765393492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 6.24500846862793, "genuineness": 4.337893962860107, "identity": 0.30277732014656067, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/d5f0cef00e082e186b557e2f08b2762e41533b44c2385668fba0316a9e87f83b.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": "d637c2cc09f98b47493292cad7b23ef1c18e143afa92d7b25c129985aa2cdb77", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6a383533e5f5422e69f48a97f9c8dc9576a3ff73b549d7d81e0e1756cefb88fc", "generation_seconds_batch": 22.71209559997078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28218644857406616, "target_z": 0.19726562960457775, "ce": 5.71682071685791, "genuineness": 4.570107460021973, "identity": 0.22195520997047424, "hypothesis": "De weg gaat linksaf naar de brug. Het loopt verder tot een kleine houtdhijk. Ik wacht aan de andere kant.", "wer": 0.3333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d637c2cc09f98b47493292cad7b23ef1c18e143afa92d7b25c129985aa2cdb77.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "d70e3ee2392a404bb3ae0e3b4c28f90bf40497818e0eee4cda2e5fb8f21fff01", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "33e809688f17cf486dfe628cf9ebb3158a0ec288e5af646deeb7d01ea6c37239", "generation_seconds_batch": 19.076883016969077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 6.086154937744141, "genuineness": 4.444586753845215, "identity": 0.5406957864761353, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d70e3ee2392a404bb3ae0e3b4c28f90bf40497818e0eee4cda2e5fb8f21fff01.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": "d748fb091d2327f2fd40090120651f919ae409dec83a13bcb40e8820b04a2ead", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "daa68403b49c3229c25dbf2ef7c6d640bccf186ecd3336c3fee26a76849ff36f", "generation_seconds_batch": 20.798191213980317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13009630143642426, "target_z": -0.07617186537224652, "ce": 5.839932441711426, "genuineness": 4.65797233581543, "identity": 0.7320644855499268, "hypothesis": "La carretera gira a la izquierda tras el puente. Así que hasta la pequeña puerta de madera. Te esperaré al otro lado.", "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_Intoxication_Altered_States_of_Consciousness/d748fb091d2327f2fd40090120651f919ae409dec83a13bcb40e8820b04a2ead.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": "d7d2c64d305ded32377aa3d5efb255ccea09d19c35d4234876091e4746728fb9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "496d605991599c51126674a9df1da9e2abc9b0d4b8087412b848552e55037f33", "generation_seconds_batch": 15.9018787589157, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13362696766853333, "target_z": -0.06982420545951422, "ce": 5.80021858215332, "genuineness": 4.7332844734191895, "identity": 0.6080574989318848, "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_Intoxication_Altered_States_of_Consciousness/d7d2c64d305ded32377aa3d5efb255ccea09d19c35d4234876091e4746728fb9.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "d806466240fba2ce2cdcdec69ba75fd5adb73e558440d86b1eff5d4e5b73de38", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "085cac259dd2c5674e28627b50af1d7dc7bab73b8f0eb2664e6daa22b4a4a531", "generation_seconds_batch": 23.431428688927554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04101492464542389, "target_z": -0.2363281212326182, "ce": 5.903473377227783, "genuineness": 4.381826400756836, "identity": 0.5294472575187683, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/d806466240fba2ce2cdcdec69ba75fd5adb73e558440d86b1eff5d4e5b73de38.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "d823915950c09130837a2b81487fa6d319f23ba81e3db83fdd349d147c43a317", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "292b0450b1bc33eace8469e5b15acb7073a4691357b70b4d9bf653e56556a007", "generation_seconds_batch": 22.28433325397782, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013855963945388794, "target_z": -0.2851562558603717, "ce": 6.086154937744141, "genuineness": 4.720732688903809, "identity": 0.6681579351425171, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/d823915950c09130837a2b81487fa6d319f23ba81e3db83fdd349d147c43a317.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "d863a3ba2601eada892dd47a39c8b6a78009438b2e581fe9cfbef851e16f7c92", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "76e96c3e36ae19f7c958438a0ea24c87708abeeceac7c3ac8217e436d4217f98", "generation_seconds_batch": 29.855559173040092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0019060224294662476, "target_z": -0.3066406329533616, "ce": 5.824047088623047, "genuineness": 4.833701133728027, "identity": 0.8212506771087646, "hypothesis": "Euh j'ai trouvé la petite boîte elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d863a3ba2601eada892dd47a39c8b6a78009438b2e581fe9cfbef851e16f7c92.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "d8793cf767d72d52ec00845aebe2f3859763973c7135285992580cf3cd7dd4e3", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "37d742cc21ceeb99387428559f5e6c1ba2a6063cda84c5d3184bd6669284c8ac", "generation_seconds_batch": 25.95963193802163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014942318201065063, "target_z": -0.2832031379765373, "ce": 6.316492557525635, "genuineness": 4.65797233581543, "identity": 0.5318893790245056, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d8793cf767d72d52ec00845aebe2f3859763973c7135285992580cf3cd7dd4e3.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "d9796b9b44120d596d98178c0c21dff8531470623bf1650884ec0d1e0eff7db8", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "60616de3646e8385554c1995024f71cc8967de6dc2abec4f6b6e7334046346b5", "generation_seconds_batch": 24.302002532058395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.000819668173789978, "target_z": -0.308593750837196, "ce": 5.967014789581299, "genuineness": 4.821148872375488, "identity": 0.69124436378479, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d9796b9b44120d596d98178c0c21dff8531470623bf1650884ec0d1e0eff7db8.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "d9b2bc8fdc408ccd0712d8533bb6b0c263cc93c5fec167e434ddd7188820b61b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9dc94f99ab51a16f33f519123a557736587c12f105b0ff86299a063b692c6dba", "generation_seconds_batch": 22.93600436602719, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.078212261199951, "genuineness": 4.419482707977295, "identity": 0.4624759554862976, "hypothesis": "The door is still open. I put your coat uh on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d9b2bc8fdc408ccd0712d8533bb6b0c263cc93c5fec167e434ddd7188820b61b.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": "d9bc466778f5d1687a6b8d4c3cee834b9ce0b53687a73fde4dc56d4fd2d660e4", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "de690d6075dd75539500b134b3ce51a279b7c71dea8cdfcaaecb19ac36ca2b86", "generation_seconds_batch": 18.515709316008724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06382844597101212, "target_z": -0.1953124983256081, "ce": 6.054384231567383, "genuineness": 4.6705241203308105, "identity": 0.6863012909889221, "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_Intoxication_Altered_States_of_Consciousness/d9bc466778f5d1687a6b8d4c3cee834b9ce0b53687a73fde4dc56d4fd2d660e4.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "d9cd2085bfaaf7a5833aae41a1a5563935305e2058f1e8a5241aa85e405573d5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ff244dc297ab2599f35fb09deab425606977230568cf3c282c5a181cdc5514b5", "generation_seconds_batch": 23.508388133952394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 6.125868320465088, "genuineness": 4.432034492492676, "identity": 0.7106368541717529, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/d9cd2085bfaaf7a5833aae41a1a5563935305e2058f1e8a5241aa85e405573d5.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "da43f2d54ff87702c5232d70b7ec10339e1cd2dea24d3df70f15e4e490698989", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a5e87a3cc4c887711f9a658c17dcc6551a0a23a48ec85c25aa49dd40126b3d8e", "generation_seconds_batch": 22.84294660994783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.034496769309043884, "target_z": -0.2480468821161656, "ce": 5.879645347595215, "genuineness": 4.7458367347717285, "identity": 0.7792156934738159, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/da43f2d54ff87702c5232d70b7ec10339e1cd2dea24d3df70f15e4e490698989.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "da4939968b8f96a14b53d39101fadc0a7e1d2e7e0f3f0e8d3bf3c94f0e43e50e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ac7db147c0f276eccf8fc45e87b2500f7f88c98938a205d45dfdac7dad4e1bd6", "generation_seconds_batch": 25.95963193802163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03992857038974762, "target_z": -0.2382812391164526, "ce": 6.308549880981445, "genuineness": 4.532451152801514, "identity": 0.2585492432117462, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/da4939968b8f96a14b53d39101fadc0a7e1d2e7e0f3f0e8d3bf3c94f0e43e50e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "da4dc5f1bf2dc9912352561f066e0b146e69b0b4d421c616c3e8163150286378", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d6d6dd7a196db7f34aef07a21b73a83a223acd66c094b247d722caea8424ff2c", "generation_seconds_batch": 23.57007114600856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18835225701332092, "target_z": 0.028564456212160083, "ce": 5.998785495758057, "genuineness": 4.406930446624756, "identity": 0.7411566972732544, "hypothesis": "Ik heb het een klein doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/da4dc5f1bf2dc9912352561f066e0b146e69b0b4d421c616c3e8163150286378.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": "da9616f6adec41673e180074c30444c408edb9551291215e967130aa490b2a53", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "4032df3ed1130a1d6dc65b253870419da54ba540c1ae22ff113d410ed5a9a658", "generation_seconds_batch": 17.747690104995854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05622393637895584, "target_z": -0.2089843770929899, "ce": 6.324435234069824, "genuineness": 4.494794845581055, "identity": 0.2934860587120056, "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_Intoxication_Altered_States_of_Consciousness/da9616f6adec41673e180074c30444c408edb9551291215e967130aa490b2a53.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "da9c6c85e0589c98a2d0d23970590a1f471d5574ffc99d8651b215f1cc1aeddd", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8c7f2a664474e19328c38569886d814323aea5a355553607427d8db74bdfd51c", "generation_seconds_batch": 22.28433325397782, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07197613269090652, "target_z": -0.1806640606163091, "ce": 6.117925643920898, "genuineness": 4.7332844734191895, "identity": 0.7681220769882202, "hypothesis": "Je vais te dire, j'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.21052631578947367, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/da9c6c85e0589c98a2d0d23970590a1f471d5574ffc99d8651b215f1cc1aeddd.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "67c52d50165f292904b22cd02e822d318b56a39d344028095df610c0257caf3d", "generation_seconds_batch": 15.696308327023871, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008424177765846252, "target_z": -0.2949218720698142, "ce": 6.4912309646606445, "genuineness": 4.281409740447998, "identity": 0.6137168407440186, "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_Intoxication_Altered_States_of_Consciousness/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "dbe072c4fb74b7ad620cf34f327b68b6a0c8e882f18739af110ebf591790f964", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3cb4b8d7ad69ccdd9ee4e092abb25ea3e54dfc1a516237369183512ec7ec9eee", "generation_seconds_batch": 24.686092138988897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05459439754486084, "target_z": -0.21191406731387674, "ce": 6.181467056274414, "genuineness": 4.469690799713135, "identity": 0.3921416997909546, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/dbe072c4fb74b7ad620cf34f327b68b6a0c8e882f18739af110ebf591790f964.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": "dbe5a8d35774cfee030290f6f506e418d20b77945218850cd0624178e02b6890", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "708ae97e006c764afb2166ad5c863233376d2163c43e625652c524df950d664b", "generation_seconds_batch": 18.361891373060644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014942318201065063, "target_z": -0.2832031379765373, "ce": 5.95112943649292, "genuineness": 4.494794845581055, "identity": 0.6852014660835266, "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_Intoxication_Altered_States_of_Consciousness/dbe5a8d35774cfee030290f6f506e418d20b77945218850cd0624178e02b6890.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "dc299c5db642db00b78b232f59893825676881d9a53352680faf20fab960a272", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8909ac9af9ef62d9c7d3c92f34e636e4423fb1a79fd515e9c0427b71ac26a17e", "generation_seconds_batch": 22.239078488084488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02689225971698761, "target_z": -0.2617187608835474, "ce": 6.09409761428833, "genuineness": 4.570107460021973, "identity": 0.5038046836853027, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/dc299c5db642db00b78b232f59893825676881d9a53352680faf20fab960a272.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "dc53b7003003bb57f9d40409ed04de76c51171a7f34d2456e4644e9396acf21e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5b43873704656cd1a0ea3821c5c194da9ff4caa96571a83bc76b64c3ff485060", "generation_seconds_batch": 23.87461977498606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033410415053367615, "target_z": -0.25, "ce": 5.792276382446289, "genuineness": 4.7458367347717285, "identity": 0.7475299835205078, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/dc53b7003003bb57f9d40409ed04de76c51171a7f34d2456e4644e9396acf21e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "dc78a5c2298f15c53989f70e475362b2e497f53ad7f0a969740c10b9e0ea087a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a3455202ccf2f7585437982f8d9e85ec54163040ba79f7c35aba043ce3549d99", "generation_seconds_batch": 24.509553702082485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04427400231361389, "target_z": -0.2304687407908445, "ce": 6.221180438995361, "genuineness": 4.632867813110352, "identity": 0.37306636571884155, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/dc78a5c2298f15c53989f70e475362b2e497f53ad7f0a969740c10b9e0ea087a.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": "dc8616a4251f4e5292c677a8405d09d1e08b6a661d8cb020823c21bb68f85580", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b1dde67debebf214d2edf33d833db42dda843fb407b586e8e770ffbe5a25de1a", "generation_seconds_batch": 17.742652900982648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016028687357902527, "target_z": -0.2812499933024324, "ce": 5.756534099578857, "genuineness": 4.68307638168335, "identity": 0.48329421877861023, "hypothesis": "Les clés sont sur la table de la cuisine, j'ai regardé dans le tiroir, puis près de la fenêtre, prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/dc8616a4251f4e5292c677a8405d09d1e08b6a661d8cb020823c21bb68f85580.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "dd4ed612939fb37c9f06f39b862b3fde669019b4b652b05362e090f6984bf2c0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6a9d9f43c2320d4a44f15f151dd566b9627fe0cfb38b48a4c0c9e00486e572f3", "generation_seconds_batch": 23.002738212933764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18142671883106232, "target_z": 0.01611327612217478, "ce": 5.967014789581299, "genuineness": 4.287685871124268, "identity": 0.6207427978515625, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/dd4ed612939fb37c9f06f39b862b3fde669019b4b652b05362e090f6984bf2c0.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": "dd7356e244016df6c96248bdc14ed4962c885910655c8d973d0dff27318960f7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fcae088835712f1d9fcdafa446813bce256b301c10acc749afce0ab183161e11", "generation_seconds_batch": 23.073236754047684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01928776502609253, "target_z": -0.27539061286065863, "ce": 5.998785495758057, "genuineness": 4.507347106933594, "identity": 0.44481930136680603, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik los het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/dd7356e244016df6c96248bdc14ed4962c885910655c8d973d0dff27318960f7.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": "dd92bc0dde7b0749b456c050e90160e2317e4f3cb8dbeff3668ec7bf4f8d6810", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "035336af166d05c673805583197011a34294f9b122f7d89ff377b6a73daa4f07", "generation_seconds_batch": 20.798191213980317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.059483014047145844, "target_z": -0.2031249966512162, "ce": 6.006728172302246, "genuineness": 4.545003414154053, "identity": 0.5784623026847839, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/dd92bc0dde7b0749b456c050e90160e2317e4f3cb8dbeff3668ec7bf4f8d6810.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "dd933693c3e5a00299b3c7d0abfa5ea17644b178bdbb9fd76da3db2db6a68818", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "321e6662663dd5c77873d7f43f5fa1b904ef710b77c22032637e7091d5bd55ea", "generation_seconds_batch": 25.602365639060736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05024896562099457, "target_z": -0.21972656563948484, "ce": 6.149696350097656, "genuineness": 4.557555198669434, "identity": 0.5845516920089722, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/dd933693c3e5a00299b3c7d0abfa5ea17644b178bdbb9fd76da3db2db6a68818.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "ddaddad359aeef3de22165a551a17c1673a220dc80e3a5fc00dc0030759f8ceb", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8b07a12f0ca7f2f16427ffbdf0ef405f8f4b0f21e852d951d0a5f0cb2e715764", "generation_seconds_batch": 30.109883110038936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.24500846862793, "genuineness": 4.2751336097717285, "identity": 0.3052865266799927, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/ddaddad359aeef3de22165a551a17c1673a220dc80e3a5fc00dc0030759f8ceb.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": "df96b5cd258003474108988dd3e8d67097d3c8358441881dc6e1cc01fbc7f5b9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c80fabce764d20c66b6d71c58f1ae5ac8d15654de93de8e7c949b28db2aea67a", "generation_seconds_batch": 24.146354010910727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031237691640853882, "target_z": -0.2539062625579393, "ce": 5.919358730316162, "genuineness": 4.833701133728027, "identity": 0.8337979316711426, "hypothesis": "Quelqu'un a déplacé la petite uh chaise bleue. Elle était ici, près la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/df96b5cd258003474108988dd3e8d67097d3c8358441881dc6e1cc01fbc7f5b9.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "dfb1d980d13eca2cc2a7a720ae80d86705ac08bd278d1265ffeb07186cf40911", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ca662ed35cf379165260e3363e80f2c660ea4db32dc2e7d9c29a4b33f948f1fa", "generation_seconds_batch": 24.468697185977362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0019060224294662476, "target_z": -0.3066406329533616, "ce": 6.1894097328186035, "genuineness": 4.7081804275512695, "identity": 0.5230407118797302, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/dfb1d980d13eca2cc2a7a720ae80d86705ac08bd278d1265ffeb07186cf40911.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "dfe2bb37ff71aa2c75355ca2c33cdd6364d7fd2f0ee750fb29910dad1ac09557", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8c35d8860c29b73a3e17df818f9a9e53a46027f113c25c3919b5a71aca1d5660", "generation_seconds_batch": 23.515260620974004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014942318201065063, "target_z": -0.2832031379765373, "ce": 6.006728172302246, "genuineness": 4.570107460021973, "identity": 0.5662716627120972, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/dfe2bb37ff71aa2c75355ca2c33cdd6364d7fd2f0ee750fb29910dad1ac09557.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "e00e3c0ef70b23886ab0bf9d161a86ab6bbea20104e16833eb049639b7ecc781", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d9c2a48b832d03f62adcd76b6b8f8b44dd5ff1968ed7e6044dc356947bfaf420", "generation_seconds_batch": 23.76958071894478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 5.788304805755615, "genuineness": 4.7081804275512695, "identity": 0.5789059400558472, "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_Intoxication_Altered_States_of_Consciousness/e00e3c0ef70b23886ab0bf9d161a86ab6bbea20104e16833eb049639b7ecc781.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "e0de8b6ca770d58a4b2add59a02d6176805c47045bec000f7f379dee30c9f120", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "74bc5af66652a2b03a0676a32fbcd3f407d0458ee750dc8525ddd88095c84f13", "generation_seconds_batch": 23.028563763946295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.040471747517585754, "target_z": -0.2373046801745354, "ce": 6.403861999511719, "genuineness": 4.645420074462891, "identity": 0.559698224067688, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e0de8b6ca770d58a4b2add59a02d6176805c47045bec000f7f379dee30c9f120.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": "e13b7e0d84f625703a799b9f58b480b6bd5408ccf9811d98e063352f48d48ece", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3861c69082005dbf0436d360ab246b1d1c059854374d059bee03d2c0b623ea1d", "generation_seconds_batch": 16.857233191025443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08012381941080093, "target_z": -0.1660156229070101, "ce": 6.141753673553467, "genuineness": 4.21237325668335, "identity": 0.3809768259525299, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e13b7e0d84f625703a799b9f58b480b6bd5408ccf9811d98e063352f48d48ece.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "e15c443013c56b8da111c2dcb87ddd18a5b444e56216c7336ef6f9b2ce0becc7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1e6eec7bf61ff43683937e35782919e3c52ca89eefa8c5a6120be156811ffb52", "generation_seconds_batch": 25.32544534804765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 6.173524379730225, "genuineness": 4.406930446624756, "identity": 0.5964411497116089, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/e15c443013c56b8da111c2dcb87ddd18a5b444e56216c7336ef6f9b2ce0becc7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "e163546eeea9826a95f0929288944f96e37c330b6262ba1bcfee451b7da3f5e8", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b6a8fdd43b86538c15d41b35b97dcb6804243849e367b1edde43c80192e9c3cd", "generation_seconds_batch": 24.468697185977362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009510532021522522, "target_z": -0.2929687541859798, "ce": 6.181467056274414, "genuineness": 4.65797233581543, "identity": 0.503718376159668, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e163546eeea9826a95f0929288944f96e37c330b6262ba1bcfee451b7da3f5e8.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "e1bfd24f6ef3060d726f1b29d16ff005b139a7d8be265aedb988ad0124f1c571", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e4c0c3d42c8bb57c7e4083a44a2fa43d018c5d911df4bc9e4a8c1c822bbdaf65", "generation_seconds_batch": 22.866261070012115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05731029808521271, "target_z": -0.20703124581402021, "ce": 5.919358730316162, "genuineness": 4.883909225463867, "identity": 0.6391485929489136, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e1bfd24f6ef3060d726f1b29d16ff005b139a7d8be265aedb988ad0124f1c571.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "e2409a87350205bbaa0a99286f54abe7e72c7e891ce6473f82052c24442cc6c7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cd06c798a16cdff0d09668049436483e842d9a2b636a75b5fa6e034befc4babd", "generation_seconds_batch": 22.169364113011397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009510532021522522, "target_z": -0.2929687541859798, "ce": 5.700935363769531, "genuineness": 4.921566009521484, "identity": 0.6860446333885193, "hypothesis": "Je trouvai la petite boîte, elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e2409a87350205bbaa0a99286f54abe7e72c7e891ce6473f82052c24442cc6c7.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": "e253269180feaa3e14f406c37cd5fc6b7cc3e871acdbb436ad88846009107353", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b09a72850be62829faa439bd61b5967be9c66f801fb87b08670fd5ef80552ee1", "generation_seconds_batch": 26.3502779599512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.052964866161346436, "target_z": -0.2148437441396283, "ce": 5.792276382446289, "genuineness": 4.457139015197754, "identity": 0.7591902017593384, "hypothesis": "Les clés sont sur la table de la cuisine. j'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e253269180feaa3e14f406c37cd5fc6b7cc3e871acdbb436ad88846009107353.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "e262839ad8178237a9293487743d582b3db2a967b3fd249b2e2b14e74a7b64f5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c28cf71f4f148094a424c8f8ca881f7411554190bd1a90614f14135d04424efb", "generation_seconds_batch": 25.02730117808096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009510532021522522, "target_z": -0.2929687541859798, "ce": 5.990842819213867, "genuineness": 4.808597087860107, "identity": 0.7203096151351929, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e262839ad8178237a9293487743d582b3db2a967b3fd249b2e2b14e74a7b64f5.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "e268c92d2705d28293730b01fc8964cfbdb04c508089af32af4ae24a05f8cc35", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1eed4fe08f7506f6e64a422b38b266b401c3a52e9fbb1a2971062cda4222511d", "generation_seconds_batch": 27.793263258994557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03829902410507202, "target_z": -0.2412109427324747, "ce": 5.919358730316162, "genuineness": 4.645420074462891, "identity": 0.5797805786132812, "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_Intoxication_Altered_States_of_Consciousness/e268c92d2705d28293730b01fc8964cfbdb04c508089af32af4ae24a05f8cc35.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "e2a6e074083431a2cd20d34aae9daf694ec56dfa893d9854d3d88e345bdda10e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "06f04fb661b72130daabb23009ca554b9d5369c6cebf08793c69a8aef8046bb3", "generation_seconds_batch": 17.12039369100239, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03992857038974762, "target_z": -0.2382812391164526, "ce": 6.117925643920898, "genuineness": 4.293961524963379, "identity": 0.667586088180542, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e2a6e074083431a2cd20d34aae9daf694ec56dfa893d9854d3d88e345bdda10e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "e2b8405ca63c2938b8edf3f6a1ba0e35facce6c457e93d44b72fa6ccd78e6bac", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "acad6bd4a926290c2a199424c834ee1c563a64511c733c157d306ff6d4429bc4", "generation_seconds_batch": 24.97923737706151, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01656205952167511, "target_z": -0.3398437441396283, "ce": 6.070269584655762, "genuineness": 4.7332844734191895, "identity": 0.680935800075531, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e2b8405ca63c2938b8edf3f6a1ba0e35facce6c457e93d44b72fa6ccd78e6bac.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "e2c3d4de217ba3b5f00b51721b977fb59c3be661e304c1cafbb871209ebf1bcf", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "629e6491104fafc6e97089dee0ec732040615919aae5603dd61276f58a637ced", "generation_seconds_batch": 24.044635790982284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03395359218120575, "target_z": -0.2490234410580828, "ce": 6.284721851348877, "genuineness": 4.444586753845215, "identity": 0.5005887746810913, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e2c3d4de217ba3b5f00b51721b977fb59c3be661e304c1cafbb871209ebf1bcf.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "e2f58ad029c48398708ed28bce483ba517c1dad1fe6e0ac44e93f73832372afc", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "56daedddcb47be5d5134b6ab5a3ff4df74fa9d02c407a196afa3acead8c8a13f", "generation_seconds_batch": 19.270495526026934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04536035656929016, "target_z": -0.2285156229070101, "ce": 6.308549880981445, "genuineness": 4.607763767242432, "identity": 0.59046471118927, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e2f58ad029c48398708ed28bce483ba517c1dad1fe6e0ac44e93f73832372afc.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "e36fdf5023e4eb9de25a40e907a699c0713b9a6a151297530eccf976461a712d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "91e451527fd0698b433b6ae9c739ea9c478ec639798d6ca733ebfcc8562ca387", "generation_seconds_batch": 24.7532375799492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 6.046441555023193, "genuineness": 4.381826400756836, "identity": 0.48259037733078003, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e36fdf5023e4eb9de25a40e907a699c0713b9a6a151297530eccf976461a712d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "e3b2c300b8ce5abff51a8f045c05f272f5511a2fe808236e1349982b25bd1e23", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "09e1b43d0909bae1ae67a5322e2077c3b93afcc9ea68cdd001b71ebbb927b5d1", "generation_seconds_batch": 24.03251116699539, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 6.38003396987915, "genuineness": 4.582659721374512, "identity": 0.369853675365448, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/e3b2c300b8ce5abff51a8f045c05f272f5511a2fe808236e1349982b25bd1e23.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "e3cf47b41c8976f043eb273f52329b0d9be4b8314fa8695f544905958e7f47a9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "40d5fbdb280dc6f577700caf8f3f6c829a135116946e5c6991d4d1bc7f92e29c", "generation_seconds_batch": 24.67631406104192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05893982946872711, "target_z": -0.20410156898826864, "ce": 5.919358730316162, "genuineness": 4.2751336097717285, "identity": 0.37368860840797424, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/e3cf47b41c8976f043eb273f52329b0d9be4b8314fa8695f544905958e7f47a9.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "e3d687c2f5521941c6be5b8f7f365cad34c3736ef1f9e4367b63340a8aba8b75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b20822ee08275c70e1451a614a0e7aa5cb05724db1dba1fde3c3a08fe9bb9222", "generation_seconds_batch": 22.107437659986317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013855963945388794, "target_z": -0.2851562558603717, "ce": 6.24500846862793, "genuineness": 4.532451152801514, "identity": 0.4317513108253479, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you were ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e3d687c2f5521941c6be5b8f7f365cad34c3736ef1f9e4367b63340a8aba8b75.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "e47446ccac3809177af2d1cd0c82d755ec593a60d31549ec4046c1a803fb3c4d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d11f7e8b28dfcbae30a3a352305d35a3bec44bfd5b838d36602b44bb0fa9a990", "generation_seconds_batch": 24.76317036501132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 5.788304805755615, "genuineness": 4.162164688110352, "identity": 0.6353815793991089, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e47446ccac3809177af2d1cd0c82d755ec593a60d31549ec4046c1a803fb3c4d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "e51c2274dbcaf325bd3d2b3530a7b18dbb7e7df1e446b753a9db9bdea68147e3", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d5df49eab22f953521e003a2ad42e17c08d2800fdb2e29cf257ce4b7f97199c5", "generation_seconds_batch": 17.897987911012024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031237691640853882, "target_z": -0.2539062625579393, "ce": 6.221180438995361, "genuineness": 4.833701133728027, "identity": 0.6013981103897095, "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_Intoxication_Altered_States_of_Consciousness/e51c2274dbcaf325bd3d2b3530a7b18dbb7e7df1e446b753a9db9bdea68147e3.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "e529ec1472326222ff47a325019333d2cb11a729531f1a8b170bb6eebe9691e2", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "14aa5d8d477295d15b019efbcb5b667b274cc75c502b41a7f80f19c5ae3f7b72", "generation_seconds_batch": 23.419560850947164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017115041613578796, "target_z": -0.279296875418598, "ce": 6.038498878479004, "genuineness": 4.406930446624756, "identity": 0.5683885216712952, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e529ec1472326222ff47a325019333d2cb11a729531f1a8b170bb6eebe9691e2.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "e5394ac6e87be806a3db7508115654735f93859ce38debe2e9c3f9fee74377b0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "104467c570064763b69bebef177e9d90f414dd2e7069d41ac3556b72dc1e8fb0", "generation_seconds_batch": 24.892824792070314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.117925643920898, "genuineness": 4.406930446624756, "identity": 0.3213998079299927, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/e5394ac6e87be806a3db7508115654735f93859ce38debe2e9c3f9fee74377b0.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "e53cc4731bd0e16eda89e0196ea6f267b7a5eb10ba3fc2dfbe2c8b0dc1e95b1a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "78d37bd1efa5000ada3f97acd5943560e1ef49551e47e3539d374d6ec2a06a04", "generation_seconds_batch": 24.49509399908129, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033410415053367615, "target_z": -0.25, "ce": 5.855817794799805, "genuineness": 4.758388519287109, "identity": 0.7773755192756653, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/e53cc4731bd0e16eda89e0196ea6f267b7a5eb10ba3fc2dfbe2c8b0dc1e95b1a.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": "e56097cda062e18ce45d3a1ede46b9a0324b796956fedd27834a762452ddd567", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "aea3811bc6a6bd62a073f548282d644b208e71e269451a6a645d155020f2cd4d", "generation_seconds_batch": 19.19170377997216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003525763750076294, "target_z": -0.316406249162804, "ce": 6.173524379730225, "genuineness": 4.381826400756836, "identity": 0.47441935539245605, "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e56097cda062e18ce45d3a1ede46b9a0324b796956fedd27834a762452ddd567.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "e578374646556308d23451740ea558620461ba67bff477a1277a3c547feccb83", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5051d6fe63dcc16151244756835b28fba975614afa7d38c5e7efa409299ea3b6", "generation_seconds_batch": 23.87461977498606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 5.5539960861206055, "genuineness": 4.921566009521484, "identity": 0.5524978637695312, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/e578374646556308d23451740ea558620461ba67bff477a1277a3c547feccb83.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "e6284eb05197bd133920e1ead695416a51e6d3e878cb585fe30a7213b9214eff", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "wording", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a303a05705f1a4417be2cdc887f5e09ad880b87e2a0d447b3a399b4d95c96085", "generation_seconds_batch": 16.534675283008255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02689225971698761, "target_z": -0.2617187608835474, "ce": 6.403861999511719, "genuineness": 4.331617832183838, "identity": 0.5290440320968628, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e6284eb05197bd133920e1ead695416a51e6d3e878cb585fe30a7213b9214eff.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "e633302fd8bb329d3746c596b56fca40d5e7a1330f470da9db6730ee2e11f207", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e9a6e4d66642e04194661cf2791526249202223b2fad8d133e9a3b7ce29f228f", "generation_seconds_batch": 18.82229852594901, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 6.23706579208374, "genuineness": 4.331617832183838, "identity": 0.46350353956222534, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e633302fd8bb329d3746c596b56fca40d5e7a1330f470da9db6730ee2e11f207.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "e640a022eac94059a73ea945542f1f8b04b4106cfd43f361c66eb3c210698f29", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6e1a41081fd4427d29b4ba2c63861d85969b2cc2408069adcf941fa2f7f38d52", "generation_seconds_batch": 25.811902847955935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.340320587158203, "genuineness": 4.607763767242432, "identity": 0.4750382602214813, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e640a022eac94059a73ea945542f1f8b04b4106cfd43f361c66eb3c210698f29.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "9d58a300aa14a34b772b241a61f9925b58eb1d6bc6b3be5e8e474e96b4248fde", "generation_seconds_batch": 18.585244117071852, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008424177765846252, "target_z": -0.2949218720698142, "ce": 6.284721851348877, "genuineness": 4.469690799713135, "identity": 0.4947514533996582, "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_Intoxication_Altered_States_of_Consciousness/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.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": "e6fa7c4561f8060116c4e3ddf234575e76bf935d657f23fa1587332af1997255", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7f45c3f359589aed6ff810a05a5a2dbc7d3634226b4848c5eceafcd64c193fd8", "generation_seconds_batch": 26.593098626006395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.197352409362793, "genuineness": 4.607763767242432, "identity": 0.3482982814311981, "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_Intoxication_Altered_States_of_Consciousness/e6fa7c4561f8060116c4e3ddf234575e76bf935d657f23fa1587332af1997255.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": "e70752aebcc1b541c39472180be6720c491f83e846bfa9812bfc0d6fa51c7e99", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "ff503670134aa4f9ddc3879e8dda5085dd72af62c7202f7a36ed9dc5a41b7505", "generation_seconds_batch": 19.290440569981, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012769609689712524, "target_z": -0.2871093737442061, "ce": 6.078212261199951, "genuineness": 4.6956281661987305, "identity": 0.5384447574615479, "hypothesis": "Las llaves están en la mesa de la cocina. Vinía en el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.043478260869565216, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e70752aebcc1b541c39472180be6720c491f83e846bfa9812bfc0d6fa51c7e99.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "e79d48ed1654d6b59ce5d44c125a2a6bd72d3485eef5a91c8658dcbac8f3592b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "10ff20905a2e0516227ff8ab78fee5e51657879ab3fcfb203b27f264df079f34", "generation_seconds_batch": 18.673003591946326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009510532021522522, "target_z": -0.2929687541859798, "ce": 6.403861999511719, "genuineness": 4.7081804275512695, "identity": 0.2664112448692322, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e79d48ed1654d6b59ce5d44c125a2a6bd72d3485eef5a91c8658dcbac8f3592b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "e7d88ae9989a71af6d25a72fcae934346dca4bdc29ae7a92ac2292a1ee5b76ea", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5602cfee927222123e3288c2583aea613489a85051c0612661384ec441ea62a9", "generation_seconds_batch": 23.934758019982837, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01547570526599884, "target_z": -0.3378906262557939, "ce": 6.24500846862793, "genuineness": 4.519899368286133, "identity": 0.6437872648239136, "hypothesis": "Ja, ik heb het kleine 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_Intoxication_Altered_States_of_Consciousness/e7d88ae9989a71af6d25a72fcae934346dca4bdc29ae7a92ac2292a1ee5b76ea.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "e7e74ffa8057c4fa483770590289eb5c46743c1260d687b55a641f45fe71a259", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c66c0f0b686cc67badd7b58b92a97a114ea6e0b299c5dfcc006de28e6d3cf1a7", "generation_seconds_batch": 18.84203952504322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 6.181467056274414, "genuineness": 4.13078498840332, "identity": 0.3268388509750366, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e7e74ffa8057c4fa483770590289eb5c46743c1260d687b55a641f45fe71a259.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "e834884de62f187bddbaa39fbf90c7516ce97909434f3e69a84ac6c876d8af08", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cb951e72a7dd66c72d822fd9111ccee4f1134f32c20e627d43a896feb18d7acf", "generation_seconds_batch": 25.3230824500788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02146047353744507, "target_z": -0.2714843770929899, "ce": 6.173524379730225, "genuineness": 4.65797233581543, "identity": 0.78204345703125, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/e834884de62f187bddbaa39fbf90c7516ce97909434f3e69a84ac6c876d8af08.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": "e92398b815253974bae41af0e6fb4428fdd94d6e7e117185ab326eb09536b6b5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a61507055fc423294a1522bd7d9e024ade147214b5347b8a6332b9496083333f", "generation_seconds_batch": 26.232262989040464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02689225971698761, "target_z": -0.2617187608835474, "ce": 6.0305562019348145, "genuineness": 4.770940780639648, "identity": 0.6851115822792053, "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_Intoxication_Altered_States_of_Consciousness/e92398b815253974bae41af0e6fb4428fdd94d6e7e117185ab326eb09536b6b5.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "e9a0f8f8e2a8f2a3efe74655aa2e6e438f41f734c36bfbbcdcd3a6cbb5309444", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4d3903f16e8c3a702c0e2309dded117478ed26a106fccf3fb045c2cbdf4fb5f4", "generation_seconds_batch": 18.36596945405472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.041558101773262024, "target_z": -0.235351562290701, "ce": 5.879645347595215, "genuineness": 4.720732688903809, "identity": 0.6858751773834229, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e9a0f8f8e2a8f2a3efe74655aa2e6e438f41f734c36bfbbcdcd3a6cbb5309444.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "e9acfc3cea96cc3146751733dc84378cb8948353f86c090a0212cc3e7acf7166", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "fd5be384680490fa5ceaf3af47018f49328fb8c604a2e9591e282d8c89b9fc85", "generation_seconds_batch": 23.224797858973034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02580590546131134, "target_z": -0.2636718787673818, "ce": 6.213237762451172, "genuineness": 4.168440818786621, "identity": 0.3886980414390564, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/e9acfc3cea96cc3146751733dc84378cb8948353f86c090a0212cc3e7acf7166.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "9d6ccc5614a843ead02f713e66e36af1e72799ba45a89ca61d700c2ed54b17a4", "generation_seconds_batch": 16.947307890979573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.316492557525635, "genuineness": 4.645420074462891, "identity": 0.6016275882720947, "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_Intoxication_Altered_States_of_Consciousness/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "e9d5f1f252460fede5a2e6c04009a45868fbd7ec422ae7115a75c3484ad36b9b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0d997ca7798e6246d92da6f5a0f7b06866235b2f3b50368ddb4e6bb0849b7a25", "generation_seconds_batch": 19.718848824035376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.260893821716309, "genuineness": 4.582659721374512, "identity": 0.6573450565338135, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/e9d5f1f252460fede5a2e6c04009a45868fbd7ec422ae7115a75c3484ad36b9b.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": "e9d84bbf6a6cc168047d4128999567eefdd08674eb1f7a3a7eb0c1e2a374a925", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "918e7734082418c44ab0f92c8bacc8a2b96b792c789d0197d0a700ec33b69743", "generation_seconds_batch": 17.937332532019354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04101492464542389, "target_z": -0.2363281212326182, "ce": 5.935244083404541, "genuineness": 4.68307638168335, "identity": 0.7041324377059937, "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_Intoxication_Altered_States_of_Consciousness/e9d84bbf6a6cc168047d4128999567eefdd08674eb1f7a3a7eb0c1e2a374a925.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "e9e1c74157450c812844c553137e0ca1a345bb2f371e0cd36440b050bc0661db", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1c826693a1962c582cf205a29952965fe540d06499f65be4f157128ca93cc32f", "generation_seconds_batch": 23.852023339946754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04318763315677643, "target_z": -0.23242188546494943, "ce": 6.1894097328186035, "genuineness": 4.7081804275512695, "identity": 0.5060071349143982, "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_Intoxication_Altered_States_of_Consciousness/e9e1c74157450c812844c553137e0ca1a345bb2f371e0cd36440b050bc0661db.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "ea3c2ff2eb1b14b99a38fe83bb6393914b3cd23db8aa831f42a441334d4a6aba", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "wording", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7afa8cbea61a884a7fafa46e5f1515c02085c4f4759ca381c6ebfb4d5ae4ade3", "generation_seconds_batch": 17.193721253075637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05187850445508957, "target_z": -0.216796875418598, "ce": 6.181467056274414, "genuineness": 4.545003414154053, "identity": 0.4718547463417053, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/ea3c2ff2eb1b14b99a38fe83bb6393914b3cd23db8aa831f42a441334d4a6aba.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "ea8ac20308d48e7d8214f3265eb3a85b2c8b80e1c34b57dd57a2d1dfb4b98033", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "68a1359e1df8dc9eacaf75ac2eaf9d65c27cf09340314ec4686c8cf7c2cc1d16", "generation_seconds_batch": 17.416506941081025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.038842201232910156, "target_z": -0.24023438379055753, "ce": 5.748591423034668, "genuineness": 4.770940780639648, "identity": 0.5980795621871948, "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_Intoxication_Altered_States_of_Consciousness/ea8ac20308d48e7d8214f3265eb3a85b2c8b80e1c34b57dd57a2d1dfb4b98033.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "eaa84744f2143da5eab8fefbfabe2dae7dd82894a3f2e2069fc537ff0a95a63d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "926fa3d1acc665824ba14ad063810f2d03b3acd4ea5727830d9640b824ade5b4", "generation_seconds_batch": 23.91904093802441, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17151370644569397, "target_z": -0.001708978148355088, "ce": 5.967014789581299, "genuineness": 4.494794845581055, "identity": 0.6957985758781433, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/eaa84744f2143da5eab8fefbfabe2dae7dd82894a3f2e2069fc537ff0a95a63d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "eab88de9fcd4f9b05c058ade41c2b772206e4afd89216657ca1ed1da6fd611bd", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "efb83f065d85bd5f11f76542c72d509a7b666dc8bf8b74aa9339ce513e9fad73", "generation_seconds_batch": 25.87343909405172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04970578849315643, "target_z": -0.220703124581402, "ce": 5.959072113037109, "genuineness": 4.7834930419921875, "identity": 0.7282705307006836, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/eab88de9fcd4f9b05c058ade41c2b772206e4afd89216657ca1ed1da6fd611bd.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "eae598409a325d46df657889f57162c3bc573e8385593501ec8779f9789c6ec6", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d5f687c1db19f9c31b996fbb8539da6b24be62233c8202e11e514bef218d2693", "generation_seconds_batch": 20.166368718026206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10022144764661789, "target_z": -0.12988280810472125, "ce": 5.990842819213867, "genuineness": 4.68307638168335, "identity": 0.6034591794013977, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/eae598409a325d46df657889f57162c3bc573e8385593501ec8779f9789c6ec6.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "eb1337577892a67229c323c3d0470d025c93fe389e6204b2012adbabb8e58d20", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "01a2979cf716700cb3d6837dcc5b7b7c727d54ca75ed0b240d8c75165a3ca096", "generation_seconds_batch": 23.772893731016666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14394736289978027, "target_z": -0.05126953198254646, "ce": 6.165581703186035, "genuineness": 4.7081804275512695, "identity": 0.6984705924987793, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/eb1337577892a67229c323c3d0470d025c93fe389e6204b2012adbabb8e58d20.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "eb621fbf9e5bb29644d65eb6998b66b204e2cfb8ed5c24f544f8bd4102c37582", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b26e286c138bc98988e645a0555799d9a2ab83513515b8e2f947498272b293ed", "generation_seconds_batch": 16.812836272991262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06437162309885025, "target_z": -0.1943359393836909, "ce": 5.8875885009765625, "genuineness": 4.632867813110352, "identity": 0.5832396149635315, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/eb621fbf9e5bb29644d65eb6998b66b204e2cfb8ed5c24f544f8bd4102c37582.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "7c0b42f9a722cd8b271f0d33f219962d1e3a935583d21a9ae9fef7a366d72bd9", "generation_seconds_batch": 17.70324590196833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010596886277198792, "target_z": -0.2910156363021454, "ce": 6.181467056274414, "genuineness": 4.607763767242432, "identity": 0.8104754686355591, "hypothesis": "La route tourna gauche après le pont. 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_Intoxication_Altered_States_of_Consciousness/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "ebf01e13f8ca609061b9c6cbf657055d2ad0ca5e61638795451f8cd6be19f965", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3826df6e6732efae531a020ed206979320feb602a6fa499e98a903032669fb74", "generation_seconds_batch": 22.212021298939362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.213237762451172, "genuineness": 4.632867813110352, "identity": 0.2505526840686798, "hypothesis": "Ik heb een klein doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/ebf01e13f8ca609061b9c6cbf657055d2ad0ca5e61638795451f8cd6be19f965.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "ecb783698e9e9613dd4c4e2f8fae6aa2a8359dc857e3b1a03c8e2aa9402e40e7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4da09165cd59bc928efdfff01742c770ea715c36e88f5174902f4d8f901d8d69", "generation_seconds_batch": 16.9591596290702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003525763750076294, "target_z": -0.316406249162804, "ce": 6.197352409362793, "genuineness": 4.7332844734191895, "identity": 0.6789164543151855, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/ecb783698e9e9613dd4c4e2f8fae6aa2a8359dc857e3b1a03c8e2aa9402e40e7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "ecc0870c4f269c8cbf3d1aa5deeacf703518d444b1241ce872d84627c4005c0d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce5a2e78093d68d8f6664f56efc59689815f494fa4f3c2b5d487f7d5702609d6", "generation_seconds_batch": 24.579031486995518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04427400231361389, "target_z": -0.2304687407908445, "ce": 5.935244083404541, "genuineness": 4.507347106933594, "identity": 0.6643677949905396, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/ecc0870c4f269c8cbf3d1aa5deeacf703518d444b1241ce872d84627c4005c0d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "ed4d2aa46a91b8cd75ce52112ec8c15a9a508020c9fa498d1dcb3c9e15b9b5f1", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2ae23cb71213b66f996d36c5f05302423c739c035205e8294a35aa58cb5e5010", "generation_seconds_batch": 23.881106097018346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007871195673942566, "target_z": -0.3242187474884121, "ce": 6.268836498260498, "genuineness": 4.400654315948486, "identity": 0.18612395226955414, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/ed4d2aa46a91b8cd75ce52112ec8c15a9a508020c9fa498d1dcb3c9e15b9b5f1.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "ed50297e4b2e41f625a2cbeebb2a400f18ff64beeee3591c0902bb811c6e8b1b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "dca9e4780f18565fd7d91b129f4ceefad900c2b8d84a35bae7139c73f380a316", "generation_seconds_batch": 22.562676310073584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006784841418266296, "target_z": -0.3222656296045778, "ce": 6.157639026641846, "genuineness": 4.720732688903809, "identity": 0.6814184784889221, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/ed50297e4b2e41f625a2cbeebb2a400f18ff64beeee3591c0902bb811c6e8b1b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "ed7ba5537c85106abbf6c2581e18d72f25bca162165a808346f6d9ffa5f1775a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e79b6c2aaf6728974507716e9ab8c3f44de4c2edfa9d9e7666d5e4184a0a3799", "generation_seconds_batch": 17.586815714021213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 6.078212261199951, "genuineness": 4.6705241203308105, "identity": 0.5529184341430664, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/ed7ba5537c85106abbf6c2581e18d72f25bca162165a808346f6d9ffa5f1775a.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": "edbce520a2ae1e11b10cbbb4cbd584d33336dc97e2a6ee45876054b14d4a5630", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "eb7d4dee7c8354ab128aec471e60230cd3c257fc1076e7a0a714e3804664d4dd", "generation_seconds_batch": 25.85735615401063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.000819668173789978, "target_z": -0.308593750837196, "ce": 6.284721851348877, "genuineness": 4.432034492492676, "identity": 0.6093412637710571, "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/edbce520a2ae1e11b10cbbb4cbd584d33336dc97e2a6ee45876054b14d4a5630.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "edc432df5a34394168f1dc271aa05e9d95d6c3c9991012accff1788d6f007349", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9283b96b86aa4452e31907ec66aab64fcbab7aabe3ab7b888a6060188ddf8d04", "generation_seconds_batch": 24.174554062075913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.024166569113731384, "target_z": -0.3535156229070101, "ce": 6.141753673553467, "genuineness": 4.507347106933594, "identity": 0.6146423816680908, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/edc432df5a34394168f1dc271aa05e9d95d6c3c9991012accff1788d6f007349.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "edc7e5ee37c9a6a9acd2bc936fadeb7e5bf67f035887c61ee4108ac35a7a52f9", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d6af0c7f7d6656250445cd3c131017d92b3892b4f4e3584c148ee13a530ca46c", "generation_seconds_batch": 25.16338187502697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18006877601146698, "target_z": 0.013671878767381795, "ce": 5.696964263916016, "genuineness": 4.758388519287109, "identity": 0.6243538856506348, "hypothesis": "La puerta sigue abierta. He dejado tu a tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.13333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/edc7e5ee37c9a6a9acd2bc936fadeb7e5bf67f035887c61ee4108ac35a7a52f9.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "edd1aad75393634622115ed9a1051d1f06db356e19ec2c8c3322df87dd793713", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "91ca5e06bce052a0db7e5fc8d14517adb87b02bb7bd7ea0907ff5ea603876f8e", "generation_seconds_batch": 19.981276196893305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016028687357902527, "target_z": -0.2812499933024324, "ce": 6.070269584655762, "genuineness": 4.7332844734191895, "identity": 0.791988730430603, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/edd1aad75393634622115ed9a1051d1f06db356e19ec2c8c3322df87dd793713.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "edeeab63736ee4cc0203db272ef232f1eeb7557befc1815b0698eb2ef72e6b7a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2ebeb50438e9f326ff6338067659a4b5937582bb05c053013b592488c3e54843", "generation_seconds_batch": 17.354834969039075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03775584697723389, "target_z": -0.2421875016743919, "ce": 6.221180438995361, "genuineness": 4.645420074462891, "identity": 0.4363734722137451, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/edeeab63736ee4cc0203db272ef232f1eeb7557befc1815b0698eb2ef72e6b7a.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": "edfdde206a69121c1d2eb89e1a3c10bc396e5438f8a47d3e8ea36c07e4f5cd36", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "e2a9e7207c3a21c8d2777ebddbb0362b7824155e760f9969b324e360869216fb", "generation_seconds_batch": 17.742652900982648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.000819668173789978, "target_z": -0.308593750837196, "ce": 5.752562999725342, "genuineness": 4.7834930419921875, "identity": 0.720098614692688, "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_Intoxication_Altered_States_of_Consciousness/edfdde206a69121c1d2eb89e1a3c10bc396e5438f8a47d3e8ea36c07e4f5cd36.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "eeb6a9080886a3f095d7301f24e75b47055b04bdf4a5f0cf981561eb0cb901dd", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c23c4c42347a4ea17d7e5abe26293f6300d6fb1030863ea30026a08226980890", "generation_seconds_batch": 27.106877909973264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03775584697723389, "target_z": -0.2421875016743919, "ce": 6.022613525390625, "genuineness": 4.65797233581543, "identity": 0.7550722360610962, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/eeb6a9080886a3f095d7301f24e75b47055b04bdf4a5f0cf981561eb0cb901dd.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "f00fcc09cc1396c847edd049bf614da0a767308591c1442b15cb91b17cb8c89a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a9c4aad301dbb8936cc2cef3f446c09a17ce311ed70a8f37c264c2340fbd64c8", "generation_seconds_batch": 28.19265705801081, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013855963945388794, "target_z": -0.2851562558603717, "ce": 6.23706579208374, "genuineness": 4.344170093536377, "identity": 0.047187332063913345, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/f00fcc09cc1396c847edd049bf614da0a767308591c1442b15cb91b17cb8c89a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "f048223687779b236bfa0f32800e99912f800160c085178a66647ecf141a3db7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "93c3990cadd4488306021e43d9e40d645d91066e7c2272bd03803479c9d8c98a", "generation_seconds_batch": 23.928583185072057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0019060224294662476, "target_z": -0.3066406329533616, "ce": 5.8875885009765625, "genuineness": 4.720732688903809, "identity": 0.7648380994796753, "hypothesis": "He encontró la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/f048223687779b236bfa0f32800e99912f800160c085178a66647ecf141a3db7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "f11e269408efc1c7f58975d0cb5194e4f98688c91937d9fe2f90b3445faaf964", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f23ee899b1d9ae29e364eb7ce2f3930adaf2dcdbdafe9577b55ea253db942765", "generation_seconds_batch": 24.686092138988897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017115041613578796, "target_z": -0.279296875418598, "ce": 6.260893821716309, "genuineness": 4.6705241203308105, "identity": 0.26205283403396606, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/f11e269408efc1c7f58975d0cb5194e4f98688c91937d9fe2f90b3445faaf964.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "f14bd8cfce8ca6e8077111862ba17ef11c6af8a84aaac7eecefa26e2466dd213", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5f437f805d46003d700aa8e7552b9164048ace995eeae158482d3e19591727a9", "generation_seconds_batch": 22.292830382939428, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0475330725312233, "target_z": -0.22460937374420606, "ce": 5.879645347595215, "genuineness": 4.796044826507568, "identity": 0.6041287183761597, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/f14bd8cfce8ca6e8077111862ba17ef11c6af8a84aaac7eecefa26e2466dd213.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": "f1cb280d1880d6f4c17453023daefa2753e6998b63c440a0aca7eb85b4be436a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "c7ef20538792e4e48525a99eca5fa43bf1eeea6066353c0ff1a7a9cbc112314e", "generation_seconds_batch": 19.196042916970327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06382844597101212, "target_z": -0.1953124983256081, "ce": 6.070269584655762, "genuineness": 4.7834930419921875, "identity": 0.7313451766967773, "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_Intoxication_Altered_States_of_Consciousness/f1cb280d1880d6f4c17453023daefa2753e6998b63c440a0aca7eb85b4be436a.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "002c2cf148eead77733f97f15f4e22618e022f0bb617ef19dc62a6bb0ccff361", "generation_seconds_batch": 18.95929229806643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 6.09409761428833, "genuineness": 4.18099308013916, "identity": 0.6398329734802246, "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_Intoxication_Altered_States_of_Consciousness/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "f29f0bad549d72b9986f62324b3f1f47e7a159e72abf729bb2d3d4f4dba8594d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d2f8c6deca5321a27948e59c2f20c6aa0bed8b11b04b4f347e223ca72d2672c8", "generation_seconds_batch": 27.834752660011873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0475330725312233, "target_z": -0.22460937374420606, "ce": 6.213237762451172, "genuineness": 4.607763767242432, "identity": 0.36372441053390503, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/f29f0bad549d72b9986f62324b3f1f47e7a159e72abf729bb2d3d4f4dba8594d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "f2be27d2bc0cf49f2b843c2d4e5a933ffaeceaa3f4e8ff9baa027d3185e9862c", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "50d87bc2b0ecf3c4cbbc8eb6783dee813212523d8bcd0036bab6783bfa33ee8a", "generation_seconds_batch": 23.661763485055417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09967826306819916, "target_z": -0.1308593804417737, "ce": 5.752562999725342, "genuineness": 4.482243061065674, "identity": 0.07189466059207916, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/f2be27d2bc0cf49f2b843c2d4e5a933ffaeceaa3f4e8ff9baa027d3185e9862c.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "f35f1acab67a5bddcbd588f037644d07d6e82409b4e75ea35c3f008b7986fd36", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2f20be40cf6fff70d2e66e262751f28515bdf35d67d6e9383e12d3c97620be2d", "generation_seconds_batch": 24.885890766978264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006784841418266296, "target_z": -0.3222656296045778, "ce": 5.871703147888184, "genuineness": 4.2374773025512695, "identity": 0.39815643429756165, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/f35f1acab67a5bddcbd588f037644d07d6e82409b4e75ea35c3f008b7986fd36.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": "f367a16fc72ffafb15093b05c09ccad6f591d8d0e6031807a45fb5db49817747", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8dcf27fb5798abe6cce7f9d3f01493d46823d86b0a5bb1c9ef2a4ae7bb02059d", "generation_seconds_batch": 23.157490471028723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013855963945388794, "target_z": -0.2851562558603717, "ce": 5.756534099578857, "genuineness": 4.482243061065674, "identity": 0.630358099937439, "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_Intoxication_Altered_States_of_Consciousness/f367a16fc72ffafb15093b05c09ccad6f591d8d0e6031807a45fb5db49817747.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Intoxication_Altered_States_of_Consciousness-en-0", "key": "f38162c2235daf2a1168e09ddb1f712eb4a53083397246c5895f3eeae6c40ed6", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The door is still open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e1b4202d31e4695c18bf5a9c90265624f30296795b0663f993819365e476fbf8", "generation_seconds_batch": 17.516305871889926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 5.919358730316162, "genuineness": 4.494794845581055, "identity": 0.40027377009391785, "hypothesis": "The 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_Intoxication_Altered_States_of_Consciousness/f38162c2235daf2a1168e09ddb1f712eb4a53083397246c5895f3eeae6c40ed6.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "f3d1b3cb06ccce133a4f7b07b562cbd78437d2e724b89f85df8bca9c2177685d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5397431fa988b5c22268bc23cf485dfa9be852545a4d60d6fc8cbe069e13a0df", "generation_seconds_batch": 25.419156046933495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00516510009765625, "target_z": -0.3007812525115879, "ce": 5.95112943649292, "genuineness": 4.268857479095459, "identity": 0.5968776941299438, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/f3d1b3cb06ccce133a4f7b07b562cbd78437d2e724b89f85df8bca9c2177685d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "f3ffd4c1224863eb25410ee44efa32d80daf5c0d1a6ae3617aa0c0ab857b2496", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6e2840c7fcecbdd1a6ecab3827de47678a873f940074cf1597126543bdd83502", "generation_seconds_batch": 23.41696772002615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02689225971698761, "target_z": -0.2617187608835474, "ce": 6.133810997009277, "genuineness": 4.3127899169921875, "identity": 0.6953511834144592, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/f3ffd4c1224863eb25410ee44efa32d80daf5c0d1a6ae3617aa0c0ab857b2496.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": "f4c6a55a502b8cb08566b622a764b5ac2796f9a28982c2966ab4ef66ec4a9d02", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8f775871c206d406aa3513a9191937dde2d45f0f2126f5695c40f0a6fb9ba387", "generation_seconds_batch": 19.467024234938435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0812101736664772, "target_z": -0.16406250502317574, "ce": 6.125868320465088, "genuineness": 4.68307638168335, "identity": 0.6324449777603149, "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_Intoxication_Altered_States_of_Consciousness/f4c6a55a502b8cb08566b622a764b5ac2796f9a28982c2966ab4ef66ec4a9d02.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "f54e4f7ebd4c115d4777d7205da103f88e8dc9c7c5e04ce5721206ec6748f151", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "719ccd8ea4c6af8285da84f29d0aa70ea590fde899553afd2fbeea5f8b953ea4", "generation_seconds_batch": 22.60465033503715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3191226124763489, "target_z": 0.26367185197711124, "ce": 5.919358730316162, "genuineness": 4.381826400756836, "identity": 0.477112740278244, "hypothesis": "de deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/f54e4f7ebd4c115d4777d7205da103f88e8dc9c7c5e04ce5721206ec6748f151.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Intoxication_Altered_States_of_Consciousness-fr-0", "key": "f585da3f34bbb4908645a83aa41f56c87e4eca3d52f8ab4ff909bd9bce769460", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "28076329cf944870339864f3da604bed0e528f9bf53e18060ef692e2a39df67a", "generation_seconds_batch": 17.534334852942266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013855963945388794, "target_z": -0.2851562558603717, "ce": 6.070269584655762, "genuineness": 4.432034492492676, "identity": 0.764116644859314, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/f585da3f34bbb4908645a83aa41f56c87e4eca3d52f8ab4ff909bd9bce769460.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Intoxication_Altered_States_of_Consciousness-nl-0", "key": "f595f313432742d40511597fafe74e87f52494ef552216879b494ac943049012", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De deur staat nog open.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8dc8d608dbc24f74c37d80080be979f5c98590948e38ee95b80d33c9ce1b1cbc", "generation_seconds_batch": 22.919623402995057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09098739922046661, "target_z": -0.1464843770929899, "ce": 6.078212261199951, "genuineness": 4.645420074462891, "identity": 0.7101060748100281, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/f595f313432742d40511597fafe74e87f52494ef552216879b494ac943049012.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Intoxication_Altered_States_of_Consciousness-de-0", "key": "f5967418f8ef65acabd5e6bc49da5a96b8586099065c2e4aac9eeac27ffc8e81", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8d2f625ece7f39694aedae318cdc30252ac6c780e82c239200d84e349ddedaf6", "generation_seconds_batch": 24.906401372049004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04536035656929016, "target_z": -0.2285156229070101, "ce": 6.078212261199951, "genuineness": 4.65797233581543, "identity": 0.6341280937194824, "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_Intoxication_Altered_States_of_Consciousness/f5967418f8ef65acabd5e6bc49da5a96b8586099065c2e4aac9eeac27ffc8e81.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": "f5c6560eb28ab4fe365fb8f16e95a4d7f0f29b57371b646d04acc1b74b2c05d5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "76b58789e6f5109bbfbaeb6172cc48ebc6399a0ed7fe0bb686993f71151f4db4", "generation_seconds_batch": 25.85735615401063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.000819668173789978, "target_z": -0.308593750837196, "ce": 6.078212261199951, "genuineness": 4.68307638168335, "identity": 0.26906341314315796, "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_Intoxication_Altered_States_of_Consciousness/f5c6560eb28ab4fe365fb8f16e95a4d7f0f29b57371b646d04acc1b74b2c05d5.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": "f5ca6ae80650054cb7a639e61afa70e41ae4e1cd34eb09688b706af8f4b8d5ca", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "3f75f5b6f3d55b802fbb4b0b419ceab3d08fe93c267109bc2e2327a8b3944eff", "generation_seconds_batch": 17.668071747990325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06600116193294525, "target_z": -0.19140624916280405, "ce": 5.542081832885742, "genuineness": 4.281409740447998, "identity": 0.17619210481643677, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la. en daarna naast het raam nemen ze mee als je weggaat.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/f5ca6ae80650054cb7a639e61afa70e41ae4e1cd34eb09688b706af8f4b8d5ca.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "f67b75d8768cd611b3f6bab4223da493f7c04c58c408aa6bb72b9e780989972b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4b1b01bf162ab158789ac8a121c5801e2fed818c52b61591122e5a960082e91a", "generation_seconds_batch": 19.166680127964355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031237691640853882, "target_z": -0.2539062625579393, "ce": 6.181467056274414, "genuineness": 4.6956281661987305, "identity": 0.6610579490661621, "hypothesis": "Ich habe die kleine Schacht gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/f67b75d8768cd611b3f6bab4223da493f7c04c58c408aa6bb72b9e780989972b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "f6a2ac81b20a38b9936948bca08819a11622a48ed33fe43aa549e5a08760ab88", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2979bab483960cb4b95d563a5bcadeefc9d8e2ce908a2748c274282269a83ece", "generation_seconds_batch": 24.52919395104982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007337823510169983, "target_z": -0.2968749899536485, "ce": 6.1020402908325195, "genuineness": 4.808597087860107, "identity": 0.6492024660110474, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. Vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/f6a2ac81b20a38b9936948bca08819a11622a48ed33fe43aa549e5a08760ab88.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "f6d3824468fc7d8a0f0d6b581a8ff63705c7e1c5cc0f328a564a48f84e86245b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "66b42fc23e7139d41a1d1d8f72a5963505f5393a1733f61bc3d842e996f1ceaa", "generation_seconds_batch": 22.91860142594669, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002992391586303711, "target_z": -0.3046874882792566, "ce": 6.062326908111572, "genuineness": 4.808597087860107, "identity": 0.7696511745452881, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/f6d3824468fc7d8a0f0d6b581a8ff63705c7e1c5cc0f328a564a48f84e86245b.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_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": "87407d293646c1c4f5c5796aebfe4d603b12d65977f5792d68f6b4e929ed0b47", "generation_seconds_batch": 17.439405690063722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 6.1020402908325195, "genuineness": 4.268857479095459, "identity": 0.7627295851707458, "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_Intoxication_Altered_States_of_Consciousness/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.mp3" }, { "id": "heldout-de-2", "language": "de", "sentences": [ "Die Straße führt hinter der Brücke nach links.", "Geh weiter... bis zu dem kleinen Holztor.", "Ich warte auf der anderen Seite." ], "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-2", "key": "f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 129, "seconds_generated": 10.32, "mp3_sha256": "bb25af4cbb70f9238353cd8da159afcc5f9431c866f0f8b4cd58571e59749e5a", "generation_seconds_batch": 17.116291019017808, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010596886277198792, "target_z": -0.2910156363021454, "ce": 6.23706579208374, "genuineness": 4.482243061065674, "identity": 0.5813196897506714, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zum kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.09523809523809523, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "f876f82717ae8f4f2ceae7021d6dbe8d1c82df90d1139ec3d8c9d2e96dfe6938", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e0caa62c1460418473f657f8ac029617f463d28e5765a2d4dc57968408685de3", "generation_seconds_batch": 23.45053272100631, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 5.80021858215332, "genuineness": 4.808597087860107, "identity": 0.8070196509361267, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/f876f82717ae8f4f2ceae7021d6dbe8d1c82df90d1139ec3d8c9d2e96dfe6938.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "f988b812ad93de34794348058f6fd50147d96a58c6db7946e294371bcc8e6b41", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a1695102dc3fb880f66a9aea5d976486d912023c8476143b351fcb7560a74302", "generation_seconds_batch": 25.14003791997675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0019060224294662476, "target_z": -0.3066406329533616, "ce": 5.959072113037109, "genuineness": 4.7834930419921875, "identity": 0.7330834269523621, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/f988b812ad93de34794348058f6fd50147d96a58c6db7946e294371bcc8e6b41.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "fa35b4f946ade87a415db3a8d2a5ff13976d4fcf9488a1ac445100ba4d67c23b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0698419d2df5f3625550ea09e376842d7c7ed1fd43fd156b03357df5bf81dfd0", "generation_seconds_batch": 23.179909385042265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0040787458419799805, "target_z": -0.3027343703954222, "ce": 6.252951145172119, "genuineness": 4.595211505889893, "identity": 0.371001660823822, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/fa35b4f946ade87a415db3a8d2a5ff13976d4fcf9488a1ac445100ba4d67c23b.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "fa37120853e14dc2ab413fa836a4626b1fa0ffcbfa30718371ce28690ec6e2fb", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c2e8a9c2a4baea59973f801522246ae9416603424f6f4b88584e020f05d13a12", "generation_seconds_batch": 18.936011858982965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0040787458419799805, "target_z": -0.3027343703954222, "ce": 6.157639026641846, "genuineness": 4.607763767242432, "identity": 0.6036019325256348, "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_Intoxication_Altered_States_of_Consciousness/fa37120853e14dc2ab413fa836a4626b1fa0ffcbfa30718371ce28690ec6e2fb.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "fa4bac87f558f5d126f6eca491bb368136c568707ac363987ab6fba32d8a2aa1", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "523569efd8a8a8a8912eb48c96de91364e03e897159fd791aa6caed708529ec4", "generation_seconds_batch": 23.19993580505252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02580590546131134, "target_z": -0.2636718787673818, "ce": 5.871703147888184, "genuineness": 4.871357440948486, "identity": 0.5882169008255005, "hypothesis": "He encontrado la cajita. Estaba junto, la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/fa4bac87f558f5d126f6eca491bb368136c568707ac363987ab6fba32d8a2aa1.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": "fa67dd32ee62faf71691a927037fffc029ecb18d20dccae71fe23955e49d97d1", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "669a79147818d6b4a4dcd85f163a2244ffa329b3169ae16037dc822f00ee15cc", "generation_seconds_batch": 24.87803278095089, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05622393637895584, "target_z": -0.2089843770929899, "ce": 5.998785495758057, "genuineness": 4.7332844734191895, "identity": 0.6749887466430664, "hypothesis": "La route tourne à gauche après le pont. Continue. Jusqu'à la petite derrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.05, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/fa67dd32ee62faf71691a927037fffc029ecb18d20dccae71fe23955e49d97d1.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "fa98ff866d3fc29c26f2a61285c28715cf5f5790c92ee8c6d71208de306ac19a", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4aaa98ce47107fe2ade23fbfb167d6251164ad787077b98dd0ae653e83b8da58", "generation_seconds_batch": 24.73673309700098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054051220417022705, "target_z": -0.21289062625579394, "ce": 5.681078910827637, "genuineness": 4.65797233581543, "identity": 0.4887688457965851, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/fa98ff866d3fc29c26f2a61285c28715cf5f5790c92ee8c6d71208de306ac19a.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Intoxication_Altered_States_of_Consciousness-es-0", "key": "facf1fc040b5eb38c3312bab686a7d8449779f74d1ce64d871722f0eea4d5b72", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "263987a9190aa9977c2d5ef729bb8e9b1fbc135cc3c11ad1bba139168daa50ba", "generation_seconds_batch": 24.98406537505798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.041558101773262024, "target_z": -0.235351562290701, "ce": 5.748591423034668, "genuineness": 4.457139015197754, "identity": 0.7333294153213501, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/facf1fc040b5eb38c3312bab686a7d8449779f74d1ce64d871722f0eea4d5b72.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "fb0aed6cb0a65a0b580082d1d2011b10d9521cc3015710733ff7ac15198ec39b", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d036df7adb88609ce883fb4b136ef1f6b32099440c75d46ee7b351c13a79f7b0", "generation_seconds_batch": 23.61731172306463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008957549929618835, "target_z": -0.3261718653722465, "ce": 6.038498878479004, "genuineness": 4.7834930419921875, "identity": 0.7582714557647705, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/fb0aed6cb0a65a0b580082d1d2011b10d9521cc3015710733ff7ac15198ec39b.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": "fb16b25db7c6825a0547da1d03071d087c195066dffa6013804a7ff3ed370f96", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "47fbb90215d7c342837fa38da2de83e7c84133ff58cc7b34ca06eb05eb25213a", "generation_seconds_batch": 18.518555530929007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 6.221180438995361, "genuineness": 4.507347106933594, "identity": 0.4655631482601166, "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_Intoxication_Altered_States_of_Consciousness/fb16b25db7c6825a0547da1d03071d087c195066dffa6013804a7ff3ed370f96.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": "fb301cf3ebab69b4d8202192c81649b268dcb156d49a9c22b35ac0a07174a674", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "bedfd7944a73522b403a51ece6fac991767a66c799c172f61e947936481295c3", "generation_seconds_batch": 18.116234724991955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06056936830282211, "target_z": -0.2011718787673818, "ce": 6.356205940246582, "genuineness": 4.582659721374512, "identity": 0.5189672708511353, "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_Intoxication_Altered_States_of_Consciousness/fb301cf3ebab69b4d8202192c81649b268dcb156d49a9c22b35ac0a07174a674.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": "fb496d79853e3d04d53a88666de45c594dab5a197803e110b598dac381513da7", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [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": "d835876f77c6e1803ccee952c3a6ab7e38b9dcc2af20ebabf60dd512ab5e49ec", "generation_seconds_batch": 18.621240523993038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0236331969499588, "target_z": -0.2675781145350506, "ce": 6.109982967376709, "genuineness": 4.419482707977295, "identity": 0.7383019924163818, "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_Intoxication_Altered_States_of_Consciousness/fb496d79853e3d04d53a88666de45c594dab5a197803e110b598dac381513da7.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Intoxication_Altered_States_of_Consciousness-es-1", "key": "fbf32b2cf2cde7143e56661a402ef864de33fdf126f52b9875553b4390c5f412", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "42858fd53d3e9323d6d91cd7d33f991c177adb8981451514f847e8635f11527e", "generation_seconds_batch": 24.302002532058395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05187850445508957, "target_z": -0.216796875418598, "ce": 6.086154937744141, "genuineness": 4.909013748168945, "identity": 0.6585032939910889, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/fbf32b2cf2cde7143e56661a402ef864de33fdf126f52b9875553b4390c5f412.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "fc33f11bdb6851465152ed25011d0c80675d22a32e33f1dcda50720e31677904", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7d8628d472fc0b57330f72e9b2586bff47c0e2138ec7f7e2c22577ece8476e8c", "generation_seconds_batch": 23.028563763946295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04536035656929016, "target_z": -0.2285156229070101, "ce": 6.165581703186035, "genuineness": 4.6203155517578125, "identity": 0.6795734763145447, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/fc33f11bdb6851465152ed25011d0c80675d22a32e33f1dcda50720e31677904.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": "fc742aa15b8ac63f2d64eb65c16441b8d6fb7988a32121657f4146a97d9ec380", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "heldout", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "89001b83051cf739b837599d6b2b9f04a02b70e794a63bbf7a8e9d8fea7e5061", "generation_seconds_batch": 28.776582426042296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017115041613578796, "target_z": -0.279296875418598, "ce": 5.863759994506836, "genuineness": 4.607763767242432, "identity": 0.612536609172821, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter, bis zu dem kleinen Holztorch. 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_Intoxication_Altered_States_of_Consciousness/fc742aa15b8ac63f2d64eb65c16441b8d6fb7988a32121657f4146a97d9ec380.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "fc9ba0302b832a4c3785f93a050f06c5f2f7e2a3d9cffa20ba417a7bfb0d7498", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d2e83949cbf6ea6bee9b29c70dce4e855a9d9f687c1a0ce75edbfa32c9c2e462", "generation_seconds_batch": 25.151524547021836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 6.2767791748046875, "genuineness": 4.7081804275512695, "identity": 0.6865629553794861, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/fc9ba0302b832a4c3785f93a050f06c5f2f7e2a3d9cffa20ba417a7bfb0d7498.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Intoxication_Altered_States_of_Consciousness-nl-1", "key": "fcae217a2fc09af6715760e20b720c659146678e7b0af8c0f6acf3deec06cdba", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a96d8a9a1ab991c3dbd49c51442ffa64d11725c0b358a5dc47f27f498b453ebd", "generation_seconds_batch": 23.145534039940685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47229915857315063, "target_z": 0.5390625452085815, "ce": 5.824047088623047, "genuineness": 4.256305694580078, "identity": 0.5039185285568237, "hypothesis": "Ik heb het van het gokte of van het van Oetendol. We kunnen er samen in kijken.", "wer": 0.4444444444444444, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/fcae217a2fc09af6715760e20b720c659146678e7b0af8c0f6acf3deec06cdba.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "fcd4e211d0f71bceb4ffe2ed691d11a276b971c8c7ed07b9582ee5df6814570e", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6478e4b8e34251d09fc36a2ad6836eac97f56bde59b244697bf55dec3677a93a", "generation_seconds_batch": 24.884875854942948, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04807624965906143, "target_z": -0.2236328148022889, "ce": 6.3641486167907715, "genuineness": 4.7081804275512695, "identity": 0.6422052979469299, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/fcd4e211d0f71bceb4ffe2ed691d11a276b971c8c7ed07b9582ee5df6814570e.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "fd33a8154dc8c7b93e8e78a2a4890ba5fd034c9ea6a07433858b84c6c9ed70cf", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "30257df636a3609846d6aadb5c347b499b6313111d87e1b73eb96d30a256f8e2", "generation_seconds_batch": 24.424136615009047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 6.141753673553467, "genuineness": 4.570107460021973, "identity": 0.3665608763694763, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/fd33a8154dc8c7b93e8e78a2a4890ba5fd034c9ea6a07433858b84c6c9ed70cf.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Intoxication_Altered_States_of_Consciousness-fr-1", "key": "fd8c2f77e94bc4ef58bb618e115dbb5144edc7e10f3ac3f06bfdab9b837fd2b2", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d6dedf93d167a4d7d0cfd42bf5f89b690931049300eb1b171e2daf81adf48296", "generation_seconds_batch": 16.810929256957024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05622393637895584, "target_z": -0.2089843770929899, "ce": 6.109982967376709, "genuineness": 4.883909225463867, "identity": 0.6920369267463684, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/fd8c2f77e94bc4ef58bb618e115dbb5144edc7e10f3ac3f06bfdab9b837fd2b2.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "fdc5d2cf1d4eb21f787c045d1003bca19931845ebe08855238f891e1d1d72d13", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "61998243f05457e2bee96e6c435c4c57e4d7cf39ae47b75435a57cfe28c8f52f", "generation_seconds_batch": 24.12989183200989, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033410415053367615, "target_z": -0.25, "ce": 6.205295085906982, "genuineness": 4.595211505889893, "identity": 0.4467327892780304, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/fdc5d2cf1d4eb21f787c045d1003bca19931845ebe08855238f891e1d1d72d13.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Intoxication_Altered_States_of_Consciousness-de-1", "key": "ff0874c555d9369507e4b09961cfa322845d21ab6d9e68e6b53da5107a6d2a29", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "10bae3d8329f31af0ca6b96091babf9a3513adcf93b892729e36540b1994fcff", "generation_seconds_batch": 25.602365639060736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032324060797691345, "target_z": -0.2519531178838344, "ce": 6.2767791748046875, "genuineness": 4.720732688903809, "identity": 0.656470000743866, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/ff0874c555d9369507e4b09961cfa322845d21ab6d9e68e6b53da5107a6d2a29.mp3" }, { "id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Intoxication_Altered_States_of_Consciousness-en-1", "key": "ff8af65fc8298c4b6016f0e0b6ae42570f34874c5f08f3ae01c7fc8a2e176820", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "phase": "grid", "candidate": "manual-85e4ed8b7889", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ a fluctuating vocal weight, shifting from airy lightness to sudden, momentary density.\nSCRIPT:\n(Initiate with a breathy quality that seems too voluminous for the intended words.) [3.2 seconds duration] I found the little box.\n(Introduce brief moments of vocal compression, like a sudden, unfocused thought catching.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation feel slightly weighted down, as if the effort to speak is considerable.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f7b23dcb00b47d05f5fa05a1bb7a3ccf8358faeb32d351ab1d80b579f35f798e", "generation_seconds_batch": 24.73124421504326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03666949272155762, "target_z": -0.2441406195582263, "ce": 6.268836498260498, "genuineness": 4.482243061065674, "identity": 0.3825604319572449, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Intoxication_Altered_States_of_Consciousness/ff8af65fc8298c4b6016f0e0b6ae42570f34874c5f08f3ae01c7fc8a2e176820.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-de-0-seed1701-scale0.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "ea5bee836dd5ac73af78fb893d1431b52132f89d5c98c997324193c04de8da7e", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.07143295556306839, "target_z": -0.1816406195582263, "ce": 6.213237762451172, "genuineness": 4.607763767242432, "identity": 0.6081295013427734, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/de/8746beaf815942f46e673ace.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-de-0-seed1701-scale0.5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "22a37567e9d774cef66cf3848e564bc5546a9b5ab949aaa4a85aad8d76d6bbb6", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.0040787458419799805, "target_z": -0.3027343703954222, "ce": 6.252951145172119, "genuineness": 4.582659721374512, "identity": 0.5742297172546387, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/de/87b24aea33e29c40a6925380.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-de-0-seed1701-scale0.75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "2f73ab4785602df60e39d66fa0163e861bdd2d11d0a406bccdd89aff93475903", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.03992857038974762, "target_z": -0.2382812391164526, "ce": 6.268836498260498, "genuineness": 4.375550270080566, "identity": 0.4898930788040161, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/de/cbe27cae4b8898a3edf0206a.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-de-0-seed1701-scale1.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "7b77edac3e1e5b235e40463335b6dd153afc1a14584255b2357a90407bb92afa", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.05187850445508957, "target_z": -0.216796875418598, "ce": 6.268836498260498, "genuineness": 4.482243061065674, "identity": 0.5414746999740601, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/de/61cbf82a832587f8b3e51614.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-de-0-seed1702-scale0.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "0972a26d5c49306c26d4671465ad46c75e9f72cd092026b09188e25e73098b82", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.0491626113653183, "target_z": -0.2216796835233192, "ce": 6.213237762451172, "genuineness": 4.18099308013916, "identity": 0.49797719717025757, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/de/9ff5dd4cbebdf61847a8e58c.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-de-0-seed1702-scale0.5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": 129, "seconds_generated": 10.32, "ended": true, "contract_sha256": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "79448859ea48652671ae600d53f5894ab29bc8b2f95788429c9a82c84d37eff9", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.03775584697723389, "target_z": -0.2421875016743919, "ce": 6.260893821716309, "genuineness": 4.482243061065674, "identity": 0.48448646068573, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/de/e06d8afb58cc22f1b5dc5d3b.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-de-0-seed1702-scale0.75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "27a17dde1f546aeff1a1d265f9d79ed094d24c20a63805e88b48a7442e1b8f3a", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.04318763315677643, "target_z": -0.23242188546494943, "ce": 6.117925643920898, "genuineness": 4.532451152801514, "identity": 0.5168212056159973, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/de/85096f2ff56e362452060e87.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-de-0-seed1702-scale1.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "863f421dbfeb87a9d8cf5f483fed40de15700c40b669c9cf4932784b2d46d338", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.05622393637895584, "target_z": -0.2089843770929899, "ce": 6.197352409362793, "genuineness": 4.482243061065674, "identity": 0.4994739890098572, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/de/e2f372abf59acccc9628e73a.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-de-1-seed1701-scale0.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "b96777fb0a7e2274faff8ce2b9957d04595545d67222d0578f3817c12b53d8ad", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.04210127890110016, "target_z": -0.2343750033487838, "ce": 6.348263263702393, "genuineness": 4.2249250411987305, "identity": 0.36793577671051025, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/de/04c8c3676af06f518d684028.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-de-1-seed1701-scale0.5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "554cfc510c6bab7cfa3ccd9d19c3427d8b8ac6723dc51f0357f6a9fea4841d6d", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.03395359218120575, "target_z": -0.2490234410580828, "ce": 6.459460258483887, "genuineness": 4.231201171875, "identity": 0.5501566529273987, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/de/82c0c1d793a05e9423b6211d.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-de-1-seed1701-scale0.75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "11f251d3204b9858a72978b01c2d2d6b633ed714a17fd3f19fbfc68b8258a8c3", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.03503994643688202, "target_z": -0.24707032317424843, "ce": 6.348263263702393, "genuineness": 4.432034492492676, "identity": 0.6951828002929688, "hypothesis": "Ich hab die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/de/35d966799ec1d7922e523d3b.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-de-1-seed1701-scale1.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "6c8fa44bb1242ec0ed18c700c4a367c1484b19182e0f0ced04bf9ef9d86c934e", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.03992857038974762, "target_z": -0.2382812391164526, "ce": 6.395919322967529, "genuineness": 4.331617832183838, "identity": 0.5802778601646423, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/de/34b8caad53888094ad91c6cb.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-de-1-seed1702-scale0.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "5e4cb3ac7f0e7b4f2378a649048795a35e55e6cdb07251fbb35926cfd058c85c", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 6.3641486167907715, "genuineness": 4.287685871124268, "identity": 0.5477210283279419, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/de/07c0a711854ff20ebaa4ef81.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-de-1-seed1702-scale0.5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "c31a3f6540ac53116c0bd6033780ff9023e660f53ae800304af3797810be40e9", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.38003396987915, "genuineness": 4.319066047668457, "identity": 0.4676791727542877, "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/audio/emo_Intoxication_Altered_States_of_Consciousness/de/d5724b6e475787846fd10247.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-de-1-seed1702-scale0.75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "fe639268965c76cf1dffec16b96c7656b8bb81f954ca252d10c383463a6b44dc", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 6.38797664642334, "genuineness": 4.293961524963379, "identity": 0.5003636479377747, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/de/194384249ad493ac60191b5e.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-de-1-seed1702-scale1.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "53af4bdd6567eddf5cb42616241bfac1e5287b953c71a838446e29d070895c45", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.03666949272155762, "target_z": -0.2441406195582263, "ce": 6.356205940246582, "genuineness": 4.162164688110352, "identity": 0.4632527828216553, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/de/3777841d83c183f493295d22.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-en-0-seed1701-scale0.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "6fcaaa46af13a36a4f263a2201d42315f81c19b1b49683cfd315e52e9b49aa6a", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 6.300607204437256, "genuineness": 4.005263805389404, "identity": 0.37768101692199707, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/en/401f096df8d4b513ea84c6d5.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-en-0-seed1701-scale0.5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "5032288956c423fa2f98c76852fdfd19e9edd7b3d7a462860b9f5ca56d2e16e4", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.340320587158203, "genuineness": 4.250029563903809, "identity": 0.2056254893541336, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/en/00faf7e21b2bf14457955e1f.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-en-0-seed1701-scale0.75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "2a4a887b5374ac9019a64bc05e5bf271ef6d64350da20e9cd74dadbd8cc3e585", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.04970578849315643, "target_z": -0.220703124581402, "ce": 6.23706579208374, "genuineness": 4.174716949462891, "identity": 0.3924807012081146, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/en/e759f9401769aa170772fbb3.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-en-0-seed1701-scale1.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "fc50073ea34f2924d2776d69cda8a28d4daa073f1dc6c2c5b38eca0d7f125cd7", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.011683255434036255, "target_z": -0.28906249162804043, "ce": 6.24500846862793, "genuineness": 3.835810661315918, "identity": 0.32586848735809326, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/en/1fa210eb060a29312bd0d7fd.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-en-0-seed1702-scale0.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "396b2ce086a92d3f16691a6b9fcb96b638c86c7f0716a3e68e3022edf6f5b5f0", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.010596886277198792, "target_z": -0.2910156363021454, "ce": 6.284721851348877, "genuineness": 3.9299514293670654, "identity": 0.09552326798439026, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/en/b292c6c4faaabc6359ede87b.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-en-0-seed1702-scale0.5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "4984853b5ff7439519e78d1401758616e40ea171e081155d0f4f59b96f78e107", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.016028687357902527, "target_z": -0.2812499933024324, "ce": 6.24500846862793, "genuineness": 3.7918784618377686, "identity": 0.28455010056495667, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/en/385a806be7d9038fc1700afd.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-en-0-seed1702-scale0.75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "dbdf3e99e1a407bd7cc5331367a1bfb4d22f3c8d4338e540c78348c37065df29", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 6.2767791748046875, "genuineness": 4.293961524963379, "identity": 0.15438905358314514, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/en/57df4345d92f4dc2b4b983b6.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-en-0-seed1702-scale1.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "75d79698433b072fdc08a4ff929d321d24ff493d9bcd2d8e5c9aaa1bdd6b63da", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.031237691640853882, "target_z": -0.2539062625579393, "ce": 6.324435234069824, "genuineness": 4.319066047668457, "identity": 0.2064436674118042, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/en/c346f3501dbd3a0cab8bb08e.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-en-1-seed1701-scale0.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "ff437e6ed3606389b4fa5e2970677c0438794a4a75829b5850a6b136a5418afe", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.03775584697723389, "target_z": -0.2421875016743919, "ce": 6.3641486167907715, "genuineness": 4.362998008728027, "identity": 0.39760005474090576, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/en/1111e9d4ec3f5051bfba2fc2.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-en-1-seed1701-scale0.5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "70eea7b779a85c80f9b90e2798f29a689302daf0dc43c1c867d90ca0e8926aec", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.04101492464542389, "target_z": -0.2363281212326182, "ce": 6.348263263702393, "genuineness": 4.457139015197754, "identity": 0.529437243938446, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/en/077eef324f8cd5d5dbc4b14a.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-en-1-seed1701-scale0.75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "23b529218dc123cd18b3777e9e68d28c050e5ca4ac35f299a9c00a62e580c051", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.038842201232910156, "target_z": -0.24023438379055753, "ce": 6.4515180587768555, "genuineness": 4.507347106933594, "identity": 0.3598827123641968, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/en/0939319526fa5252a2490976.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-en-1-seed1701-scale1.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "07f6641d12785f18569cbcb5ad6947de8df82f40c5a86b358615344572d7ff87", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.040471747517585754, "target_z": -0.2373046801745354, "ce": 6.348263263702393, "genuineness": 4.369274139404297, "identity": 0.39157772064208984, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/en/1c3cb2350d67d1993bd35cbb.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-en-1-seed1702-scale0.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "c3e8f8a6570751cf51027337da9ff37646117fbf76c3fdaef3eed38df7eb444b", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.02580590546131134, "target_z": -0.2636718787673818, "ce": 6.340320587158203, "genuineness": 4.469690799713135, "identity": 0.3572864234447479, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/en/3b8d6e8681f29a37299e80eb.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-en-1-seed1702-scale0.5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "815f0bfe4151d8581f06a2ac1132ee4e3c2ae1ae782138a4dffa2cbc5b0413f8", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.268836498260498, "genuineness": 4.2249250411987305, "identity": 0.442719966173172, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/en/a08baa4456c2dba658ba5905.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-en-1-seed1702-scale0.75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "dd801ed31a2349171ce0345a4e8a5449777bc5881f43ebae66a6f275965dddf3", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.03666949272155762, "target_z": -0.2441406195582263, "ce": 6.403861999511719, "genuineness": 4.419482707977295, "identity": 0.5662168264389038, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/en/6eabbe67da5f1eb22ab498b4.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-en-1-seed1702-scale1.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "19b55c8af75ec790355a38050949badb048807c49d73f1fbbab78bb052ac0650", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.03829902410507202, "target_z": -0.2412109427324747, "ce": 6.213237762451172, "genuineness": 4.482243061065674, "identity": 0.5061112642288208, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/en/1a1eb1f4bc9c3cc9da623f12.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-es-0-seed1701-scale0.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "ec310f76cb27d76558cb51f84698320062b9c51acde249f650f03895ee9f702a", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.03938537836074829, "target_z": -0.23925782484864033, "ce": 6.062326908111572, "genuineness": 4.049196243286133, "identity": 0.44596436619758606, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/es/863cb934e8d915498d305454.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-es-0-seed1701-scale0.5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "ddbbbecb22f8dde063db2f0ac8fc6e1995ef959a2ed4616552a4313f4887b912", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.032324060797691345, "target_z": -0.2519531178838344, "ce": 6.260893821716309, "genuineness": 4.18099308013916, "identity": 0.44119709730148315, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/es/c9bc5458ef6735b5feb37ec0.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-es-0-seed1701-scale0.75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "b03c22b2bc3b930b76fe008702f708716415b6d6b06047314937efc7c2fadba1", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.017115041613578796, "target_z": -0.279296875418598, "ce": 6.09409761428833, "genuineness": 4.243753433227539, "identity": 0.5731481313705444, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/es/49937d9f35d92a99a2bbae7f.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-es-0-seed1701-scale1.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "2c1feac59286499d970eab8102f6a6629016bbcc3674f60f9665274510244d16", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.05622393637895584, "target_z": -0.2089843770929899, "ce": 5.7684478759765625, "genuineness": 4.3881025314331055, "identity": 0.7871750593185425, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/es/0558277f3d5db04b56aa6d74.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-es-0-seed1702-scale0.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "c98a6f05199c914295fdf2b92928950280fb1e2ee70de49a0db04906b602e4a3", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.03721266984939575, "target_z": -0.2431640606163091, "ce": 6.0305562019348145, "genuineness": 4.469690799713135, "identity": 0.6404528617858887, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/es/d75a40455739662920b0af12.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-es-0-seed1702-scale0.5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "b9ee972a3e277f0e49626fd0be98f995dd2021176c43c8a93ab9e0e896601840", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.04101492464542389, "target_z": -0.2363281212326182, "ce": 5.935244083404541, "genuineness": 4.18099308013916, "identity": 0.6658251881599426, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/es/efce2bb8f281f2c2a92dda94.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-es-0-seed1702-scale0.75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "a12bd51fa182585035768d1e02663bc885ce406db30a030a129b1c3ca80f3ba9", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.03938537836074829, "target_z": -0.23925782484864033, "ce": 6.006728172302246, "genuineness": 4.281409740447998, "identity": 0.6005600690841675, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/es/70433b3f193e7ba601a8c7e6.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-es-0-seed1702-scale1.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "99baf1e84eae6e877887dbb20874e436f5133ce8f4f9fce10ffc1e759a7c8f9e", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.04373082518577576, "target_z": -0.2314452997327617, "ce": 6.006728172302246, "genuineness": 3.8169827461242676, "identity": 0.2621382772922516, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/es/ce7887b486567c6ae6f63c10.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-es-1-seed1701-scale0.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "786a86f58389a2736a448260db6f3d64b8d92ff5c2e15523d3cd388c0dca47bb", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.016028687357902527, "target_z": -0.2812499933024324, "ce": 5.8875885009765625, "genuineness": 4.268857479095459, "identity": 0.6046935319900513, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/es/9a48fa8dab0ec1d35117c6b4.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-es-1-seed1701-scale0.5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "4cbef482be71374b62f8536b99c6f217ed17c927cc83dd84a79b660c781ec86d", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.002992391586303711, "target_z": -0.3046874882792566, "ce": 6.141753673553467, "genuineness": 4.570107460021973, "identity": 0.4981655478477478, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/es/a89f61bdd0aa8882106d0ba0.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-es-1-seed1701-scale0.75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "195e0228605c83787ebe571dbe27856332bc5a90827550133137635a3bbaca2a", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.022546827793121338, "target_z": -0.2695312592091555, "ce": 6.165581703186035, "genuineness": 4.507347106933594, "identity": 0.6860229969024658, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/es/74855b74239f8d198f70ccbc.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-es-1-seed1701-scale1.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "772000e00202f6ab94df90c37793d43ffa49a4c2639e08800368b39d24739072", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.02471955120563507, "target_z": -0.2656249966512162, "ce": 5.903473377227783, "genuineness": 4.758388519287109, "identity": 0.5365138053894043, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/es/6fa3a49c98affaaf4dc2ffb4.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-es-1-seed1702-scale0.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "c4d37ab97e6c6c893da9a244a876b07be4875b28105005fb018e8ba916598061", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 6.086154937744141, "genuineness": 4.362998008728027, "identity": 0.6066009998321533, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/es/a1440a1f553f5dc2c2ee9ff3.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-es-1-seed1702-scale0.5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "d11bea9a2fe5f98139bcdc574699fd9ae275744cfb8e4e0c5660f191fe1d745e", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.011683255434036255, "target_z": -0.28906249162804043, "ce": 6.117925643920898, "genuineness": 4.494794845581055, "identity": 0.5815513730049133, "hypothesis": "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_Intoxication_Altered_States_of_Consciousness/es/d206a9132a754a27c89d2742.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-es-1-seed1702-scale0.75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "fa542b9288128c7c4af0c3e53c8fd1bc27d9728fc3f3285a5cc4a7777f05b142", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.013855963945388794, "target_z": -0.2851562558603717, "ce": 6.205295085906982, "genuineness": 4.632867813110352, "identity": 0.6363359093666077, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/es/4a3b8db5c135fa004438dba4.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-es-1-seed1702-scale1.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "b3372f6f67777f40d2c49ca245dc2756ceb088825a893c8ec314e8d1d87bc078", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": -0.010043919086456299, "target_z": -0.3281250100463515, "ce": 6.117925643920898, "genuineness": 4.632867813110352, "identity": 0.745698094367981, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/es/2789ae4d47fb34f17237ed2b.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-fr-0-seed1701-scale0.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "d0cce5850b0c273951ad8dc7ff08345ecc2f631db7cccbee62c2514dbb2a007d", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.00516510009765625, "target_z": -0.3007812525115879, "ce": 6.165581703186035, "genuineness": 4.3881025314331055, "identity": 0.4777611792087555, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/fr/92a16df42e2231dd12a7a1c9.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-fr-0-seed1701-scale0.5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "28aa24a2ebf47cb1f66ba5c0afaae281428c8bb5ebb07dd123d2512ad70496a5", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.09409761428833, "genuineness": 4.582659721374512, "identity": 0.5269087553024292, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/fr/a8abc34e5d021d72d0f0c163.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-fr-0-seed1701-scale0.75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "16742a1b462f477d2c8733f8302f6486677fe80efc23cad10d179fc0cc7a4256", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.02689225971698761, "target_z": -0.2617187608835474, "ce": 6.316492557525635, "genuineness": 4.582659721374512, "identity": 0.5818902850151062, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/fr/2856d11e8840c2652db103ae.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-fr-0-seed1701-scale1.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "518998669e993286df677863ef608909f879ec92d66764e26abb29fba387820e", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.02580590546131134, "target_z": -0.2636718787673818, "ce": 6.173524379730225, "genuineness": 4.457139015197754, "identity": 0.8463913798332214, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/fr/dea9163bfc26ee20a8725ff4.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-fr-0-seed1702-scale0.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "c104c5417afa79004c47f474b74cf56a8d8f6afc400bf8ae8983db7ddf776acf", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.000819668173789978, "target_z": -0.308593750837196, "ce": 6.348263263702393, "genuineness": 4.720732688903809, "identity": 0.7351428270339966, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/fr/756c0f4cf819d5f33a7028c9.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-fr-0-seed1702-scale0.5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "f495baf12e73441fc61ed6a74946796b82600c505554cb5f44b147b0f2f8c8b9", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.0019060224294662476, "target_z": -0.3066406329533616, "ce": 6.078212261199951, "genuineness": 4.406930446624756, "identity": 0.8468459844589233, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/fr/1be51c492d7696877b6fc4ab.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-fr-0-seed1702-scale0.75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "57344b9feb7f32f72b65390f7070ea6bca66cee37d5790cadf4cb69385634665", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.0203741192817688, "target_z": -0.2734374949768243, "ce": 6.086154937744141, "genuineness": 4.494794845581055, "identity": 0.7062190771102905, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/fr/23bec3e96a2243a75ac9466a.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-fr-0-seed1702-scale1.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "d7b61c42d9f1307f8430533ac6f8d177d3052771baf83b7c1e83deba375c7a9c", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.007337823510169983, "target_z": -0.2968749899536485, "ce": 6.284721851348877, "genuineness": 4.7332844734191895, "identity": 0.6737525463104248, "hypothesis": "La porte 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_Intoxication_Altered_States_of_Consciousness/fr/8f21f6652a1bc03b9c35a15c.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-fr-1-seed1701-scale0.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "1cb3dc321bbb1d9b1c4e529b450f5a3cd6b65f3a31ce93238ab01c41a4607ea7", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.016028687357902527, "target_z": -0.2812499933024324, "ce": 6.284721851348877, "genuineness": 4.469690799713135, "identity": 0.7687966823577881, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/fr/53382445b669b204de61106d.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-fr-1-seed1701-scale0.5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "f0960103c7e008e391acd31183c427dad1b610fffdd6a358ddba3fee311d0946", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": -0.005698487162590027, "target_z": -0.3203125117207434, "ce": 6.205295085906982, "genuineness": 4.325342178344727, "identity": 0.42045003175735474, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/fr/b25f34e4004ed20406792ea5.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-fr-1-seed1701-scale0.75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "fdb4e10640cb4b399e268489da5df42e6fbec8ea99ab125d8cd0932cbf6dcef0", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.017115041613578796, "target_z": -0.279296875418598, "ce": 6.157639026641846, "genuineness": 4.482243061065674, "identity": 0.7322019338607788, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/fr/4202267e245fc76648454ec3.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-fr-1-seed1701-scale1.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "2ba96b7b3295872c3ed3a3f4db9ecea68ffbb2095c23dc44fc001737145e2c4a", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.007337823510169983, "target_z": -0.2968749899536485, "ce": 6.149696350097656, "genuineness": 4.519899368286133, "identity": 0.7081559300422668, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/fr/fb353f2e3ceb967faec7d956.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-fr-1-seed1702-scale0.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "5e256f9b0977c98791742d8bd9138415b2f260797dd135b4ac79d429818d1603", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 6.09409761428833, "genuineness": 4.557555198669434, "identity": 0.7476885318756104, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/fr/512378e5422a1e18c245f96d.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-fr-1-seed1702-scale0.5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "ab7e1e9dd40a7d68c8078fd5b41e6fdf2a927bb7707e66ead6cca05035376af5", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.016028687357902527, "target_z": -0.2812499933024324, "ce": 6.308549880981445, "genuineness": 4.607763767242432, "identity": 0.6623626947402954, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/fr/1282d393b581cbe69751a916.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-fr-1-seed1702-scale0.75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "a981e34e4302d626263e69e07ce1e7254614535f27623343ef44e0c8ad8b1e5a", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": -0.007871195673942566, "target_z": -0.3242187474884121, "ce": 6.054384231567383, "genuineness": 4.7332844734191895, "identity": 0.8204607367515564, "hypothesis": "J'ai trouvé le la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/fr/abe3f8796b8d58dbfa1a340b.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-fr-1-seed1702-scale1.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "cffd7260add97ae8feb934840ca16d6943230aa4ccce182a7241ed7996fd33f2", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.00516510009765625, "target_z": -0.3007812525115879, "ce": 6.109982967376709, "genuineness": 4.557555198669434, "identity": 0.8152442574501038, "hypothesis": "J'ai trouvé la 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_Intoxication_Altered_States_of_Consciousness/fr/08641c9eb345e0500f717da4.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-nl-0-seed1701-scale0.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "552df528696fe1ce95ff184943cff081f65b754e5e094f1837a2e018b25ef6b7", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.05893982946872711, "target_z": -0.20410156898826864, "ce": 6.022613525390625, "genuineness": 4.419482707977295, "identity": 0.520220935344696, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/nl/02d4b3661cbf306113ba5903.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-nl-0-seed1701-scale0.5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "cdfc92deff1d8f1c6583a143416278aa1ae51dc90dcbfa287f459bf5b73f9f42", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.04427400231361389, "target_z": -0.2304687407908445, "ce": 6.260893821716309, "genuineness": 4.306513786315918, "identity": 0.5233248472213745, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/nl/615ed64deb7499e5192abce5.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-nl-0-seed1701-scale0.75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "385cee221fd32a944ac2a1e9e4685fa1c1734b52c620e09af369341bd2c0c34b", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.1849573850631714, "target_z": 0.022460936034907078, "ce": 5.935244083404541, "genuineness": 4.243753433227539, "identity": 0.5828446745872498, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/nl/e60b5a65910544af87d0151a.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-nl-0-seed1701-scale1.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "037086cdb0c7700a0ba7f51f2058d8ed6b2b5066e951ecd36aceeb419a7e73ff", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.029064983129501343, "target_z": -0.2578124983256081, "ce": 6.0305562019348145, "genuineness": 4.306513786315918, "identity": 0.6933358907699585, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/nl/676176769df9312dc38dd0e7.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-nl-0-seed1702-scale0.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "c85aa366ff34e9a997d060689fe031897a2896ecc9faf714da9109a8d0d3d26c", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.011683255434036255, "target_z": -0.28906249162804043, "ce": 6.086154937744141, "genuineness": 4.243753433227539, "identity": 0.6217892169952393, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg, maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/nl/a8d02fb37858b8a17ab89b8d.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-nl-0-seed1702-scale0.5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "20c055f36f3d0c48bf4bde4c430dff46d935d50a12e128f14424a7c09f545a21", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.046989887952804565, "target_z": -0.22558594608125854, "ce": 6.022613525390625, "genuineness": 4.432034492492676, "identity": 0.7667818665504456, "hypothesis": "De deur staat nog open. Je hebt je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/nl/ab0d03df2b472c5611fd542f.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-nl-0-seed1702-scale0.75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "5a6da2f8ab9af0d2ac16d3ae27f456e534526482c97a714aeeb1cf3138db1b90", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.027978628873825073, "target_z": -0.2597656162094425, "ce": 6.046441555023193, "genuineness": 4.218649387359619, "identity": 0.8106047511100769, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/nl/7b171bf8dcdaaf8fc415fc45.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-nl-0-seed1702-scale1.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "19e10b982cf8a26089cf801590481d33279dbc40f38e869cb21f3b595177a606", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.02146047353744507, "target_z": -0.2714843770929899, "ce": 5.982900142669678, "genuineness": 4.595211505889893, "identity": 0.7134090065956116, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Intoxication_Altered_States_of_Consciousness/nl/b9e80259788b5fefe43bf463.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-nl-1-seed1701-scale0.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "efdc7d0423f7ae96e21231024cf3e2fe3b698c29fc1b1906fdf21e8f886dd84e", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 6.1020402908325195, "genuineness": 4.356721878051758, "identity": 0.5319513082504272, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/nl/37854673b83004d47a220530.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-nl-1-seed1701-scale0.5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "956eae8a02da53c1deb9445f752906d66722c2e92818766c69001392b79117c3", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.002992391586303711, "target_z": -0.3046874882792566, "ce": 6.117925643920898, "genuineness": 4.2374773025512695, "identity": 0.7781128287315369, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/nl/130cf0611db2bd0fee6020f2.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-nl-1-seed1701-scale0.75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "cc66ad33a1bdbfbb51bd5764ba9b05f8dbfcc4b4ddfc7484b1111d19f988f5ce", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.012769609689712524, "target_z": -0.2871093737442061, "ce": 6.181467056274414, "genuineness": 4.507347106933594, "identity": 0.6553676128387451, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/nl/3f8c4bf1354c1991aa30b20d.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-nl-1-seed1701-scale1.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "5bc55e5acbf45c15b62fd1281acdd3a2460bdb004cb094d667dc4d4f8a3d708e", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.000819668173789978, "target_z": -0.308593750837196, "ce": 6.205295085906982, "genuineness": 4.20609712600708, "identity": 0.7235622406005859, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/nl/3bad8c6ab017b43b47138c88.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-nl-1-seed1702-scale0.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "4834c26431f43c0184467c5e069f62d1ccae42904243bfae4a8cbfd53d2848ef", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.014942318201065063, "target_z": -0.2832031379765373, "ce": 6.078212261199951, "genuineness": 4.218649387359619, "identity": 0.7324485778808594, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/nl/1b4920c7a2f21175724cdba8.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-nl-1-seed1702-scale0.5", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "c4a765298721cb6390386553420756ca692303eff5b3ea4dfc4dd63e98034427", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.016028687357902527, "target_z": -0.2812499933024324, "ce": 6.117925643920898, "genuineness": 4.457139015197754, "identity": 0.41946840286254883, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/nl/80809bb892f2b54d2dba7bd0.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-nl-1-seed1702-scale0.75", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "a5af14a5be5d924bea3458f181d4a85f318a9f1ef13d4b40b46f2a09a5e458a8", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.011683255434036255, "target_z": -0.28906249162804043, "ce": 6.125868320465088, "genuineness": 4.645420074462891, "identity": 0.46299684047698975, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/nl/1d96f3de5c318da66284f596.mp3" }, { "key": "original-emo_Intoxication_Altered_States_of_Consciousness-nl-1-seed1702-scale1.0", "bucket": "emo_Intoxication_Altered_States_of_Consciousness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "2f65b0f92d1e1b39039e24902c6d25e17d858456150032c13e2cbf1a3e90edde", "mp3_sha256": "22928d78078067bde23b5d27818f28bd3f26bd20beb2f0661d9aac0d0582b2af", "task_id": "emo_Intoxication_Altered_States_of_Consciousness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Intoxication Altered States of Consciousness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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 Intoxication Altered States of Consciousness. 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": 0.018201395869255066, "target_z": -0.2773437575347636, "ce": 5.919358730316162, "genuineness": 4.231201171875, "identity": 0.5874979496002197, "hypothesis": "Ik 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_Intoxication_Altered_States_of_Consciousness/nl/bc9ba3a4cec0fb12903474ab.mp3" } ], "source_standard_audio_unchanged": true }